eess.IV — Pith

Top Pith

5

cs.CV 2026-05-20 2 theorems

AI models lag behind text-only on 3D brain MRI benchmark

by Mohammad H. Abbasi, Favour Nerrise +13 more

NeuroQA: A Large-Scale Image-Grounded Benchmark for 3D Brain MRI Understanding

Top vision-language models reach only 47.5 percent on verified questions while text statistics yield 49.4 percent.

abstract click to expand

We present NeuroQA, a large-scale benchmark for visual question answering in 3D brain magnetic resonance imaging (MRI), with 56,953 QA pairs from 12,977 subjects across 12 datasets. It spans ages 5-104 and five clinical domains: Alzheimer's, Parkinson's, tumors, white matter disease, and neurodevelopment. Unlike prior medical Visual Question Answering (VQA) efforts that operate on 2D slices or rely on narrow diagnostic labels, NeuroQA pairs every item with a full 3D volume. It evaluates 11 clinically grounded reasoning skills across Yes/No, multiple-choice, and open-ended formats. Of the 203 templates, 131 are image-grounded (answerable from a 3-plane viewer) and 72 are image-informed (ground truth from quantitative volumetry or clinical instruments). To remove text-only shortcuts, we apply answer-distribution refinement, reducing closed-format text-only accuracy from $>$80% to 44.6%; image necessity is assessed separately through an image-grounding protocol released with the benchmark. A 38-rule deterministic pipeline and two rounds of expert review verify every QA pair against FreeSurfer measurements, metadata, or radiology report fields, with zero same-subject contradictions across templates. We conduct a clinician evaluation in which two clinicians independently assess 100 frozen test items on a three-plane viewer. On closed-format (Yes/No + multiple-choice) test-public items, the best zero-shot vision-language model and a supervised 3D CNN baseline reach 47.5% and 43.7% accuracy respectively, both below the 49.4% text-only majority-template floor. NeuroQA adopts a two-tier release with public QA pairs for open-access datasets and reproducible generation scripts for datasets restricted by data use agreements (DUAs), plus subject-level splits, a held-out private test set, and an online leaderboard.

0

cs.CV 2026-07-03

Multi-expert model cuts OOD false positives on medical scans

by A.S. Anudeep, Vaanathi Sundaresan

MARVEL: Margin-Aware Robust von Mises-Fischer Expert Learning for Long-Tailed Out-of-Distribution Detection

Margin-aware nonlinear von Mises-Fisher experts plus outlier specialist achieve up to 37 percent lower error rates on three datasets.

abstract click to expand

For clinical deployment, it is essential that automated diagnostic systems remain reliable when confronted with previously unseen cases, yet deep models routinely misclassify out-of-distribution (OOD) inputs with high confidence, underscoring the need for more robust OOD detection methods. Although substantial effort has been devoted to improving model robustness, most of the existing literature assumes balanced datasets, evaluates OOD detection on coarse or non-clinical OOD sources, or lacks comprehensive assessment across diverse OOD scenarios. To address the gaps, we propose a novel methodology trained on diverse and imbalanced medical datasets and evaluated across a clinically reflective OOD spectrum. Our framework comprises three key components: (1) a Nonlinear von Mises-Fisher (NvMF) classifier capable of learning non-linear decision boundaries, with theoretical proof of its asymptotic connection to cosine classifiers; (2) a multi-expert framework in which margin-aware NvMF classifiers specialise in different regions of label distribution to better handle imbalance; and (3) an outlier expert trained explicitly to distinguish inlier from outlier data, thereby strengthening OOD detection. Evaluation on RFMiD, ISIC2019, and NCTCRC datasets demonstrates consistent improvements over state-of-the-art methods, achieving mean FPR95 reductions of 8.45%, 13.02%, and 36.90% respectively. These gains are further supported by comprehensive ablations that validated the contributions of each component. This enables reliable identification of unfamiliar cases for deferral to clinicians, supporting safer AI-assisted diagnosis in real-world workflows. Our code is available at https://github.com/redboxup/MARVEL.

0

eess.IV 2026-07-03

Self-auditing drift model leads SSIM in accelerated knee MRI

by Qing Lyu, Jianxu Wang +3 more

Self-Auditing Residual Drifting for Pathology-Preserving Accelerated Knee MRI

It adds per-slice risk scores that flag unreliable outputs while preserving lesion detail at high acceleration.

abstract click to expand

Accelerated magnetic resonance imaging reduces acquisition time, but reconstruction from undersampled k-space can blur diagnostically relevant structures or introduce failures that are not captured by global image metrics. We propose SA-RDM-DC, a Self-Auditing Residual generative Drifting Model with Data Consistency for accelerated knee MRI. The method adapts the newly proposed generative drifting paradigm to accelerated MRI by training a physics-conditioned drift field from the zero-filled reconstruction toward the fully sampled residual correction. It predicts image- and missing-k-space residual corrections, enforces data consistency with acquired k-space, uses frequency-aware and residual drifting supervision to recover fine detail, and produces dense error maps and slice-level risk scores in the same inference pass. We evaluate SA-RDM-DC on multi-coil fastMRI knee data at acceleration factors of 4, 8, and 12, with fastMRI+ pathology annotations for region-level and classifier-based task preservation, and on SKM-TEA for zero-shot and fine-tuned protocol-shift evaluation. Compared with zero-filled reconstruction, UNet-image-SENSE, DC-UNet, Score-Diffusion, ELF-Diff, SENSE-VarNet, and MoDL baselines, SA-RDM-DC achieves the highest SSIM across fastMRI acceleration factors while retaining subsecond per-slice inference and avoiding the long sampling time of iterative diffusion baselines. In pathology-aware analysis, SA-RDM-DC preserves lesion-region structural fidelity and reduces meniscus prediction instability. Its self-auditing scores strongly identify high-error reconstructions on fastMRI and partially transfer as a selective-review signal under SKM-TEA protocol shift. These results support reconstruction evaluation that jointly considers image fidelity, pathology preservation, runtime, and case-specific reliability.

0

cs.LG 2026-07-03

Stacking ensemble flags early Alzheimer's from ADNI records

by Debopriya Ghosh

Predicting Early Stages Of Alzheimer's Disease And Identifying Key Biomarkers Using Deep Artificial Neural Network And Ensemble Of Machine Learning Methodologies

After fixing missing values and imbalance, the model ranks biomarkers while comparing classifiers on standard accuracy measures.

abstract click to expand

Alzheimers disease (AD) is a brain disorder that develops slowly and mainly affects memory, thinking, language, and daily activities. It is one of the most common causes of dementia and creates many difficulties for patients as well as their families. In the early stage, the symptoms are often mild and may look like normal ageing. For this reason, many people are diagnosed late, when the disease has already progressed. At present, there is no complete cure for AD. Still, early detection can help doctors manage the condition better and take suitable steps at the right time. In this study, a machine learning model is proposed to detect the early stages of Alzheimers disease using clinical details, neuropsychological test scores, and neuroimaging-related measures. The data used in this work is collected from the Alzheimers Disease Neuroimaging Initiative (ADNI). As the dataset has missing values, iterative imputation is applied to fill them. The dataset also has class imbalance, which is handled using Borderline SVM-SMOTE. After that, feature selection is carried out using wrapper-based and embedded methods so that only important features are used for training. The selected features are divided into training and testing sets, and feature scaling is applied. A stacking ensemble model is developed using Logistic Regression, Extra Trees, Bagging KNN, and LightGBM as base classifiers. Along with this, an artificial neural network is also trained on the same dataset. The performance of these models is compared using precision, recall, F1-score, and AUC-ROC. This study aims to find the best classifier and also identify important biomarkers that may help in the early diagnosis of Alzheimers disease.

0

eess.IV 2026-07-03

Deep learning matches experts in penis MRI segmentation for 34k scans

by Jan Ernsting, Gunnar Paul Kordes +6 more

Population-Scale Segmentation of Penile Tissue in DIXON MRI using Deep Learning for Quantitative Phenotyping in Male Reproductive Health

Observer-level accuracy enables automated penile tissue volumetry in 34,412 UK Biobank participants.

abstract click to expand

Penile measurement is clinically relevant across male reproductive and urogenital health, including conditions such as micropenis, congenital and endocrine disorders, and sexual or urinary dysfunction. However, quantitative assessment of penile size has relied mainly on external length or circumference measurements, which are difficult to standardize, sensitive to measurement conditions, and unable to capture the internal portion of the penis. MRI enables volumetric assessment of the whole penis in vivo, but automated segmentation has not previously been established at population scale. Automated whole-organ volumetry would enable high-throughput phenotyping for multi-omics and clinical studies of male reproductive disease. Here, we present a deep learning framework for whole-penis segmentation in multi-channel DIXON MRI. Using a newly curated expert-annotated training dataset ($n = 145$ subjects; $13,050$ annotated slices) and a double-annotated independent test benchmark ($n = 24$ subjects; $2,160$ double-annotated slices), we optimized a 3D nnU-Net architecture. The model achieved a 5-fold cross-validation Dice score of $0.90$ and performed at observer-level accuracy on the independent test set (Dice: $0.92$; Hausdorff distance: $3.58$). We deployed the model in $34,412$ UK Biobank participants, enabling automated quantification of total penile tissue, including both external and internal components. Longitudinal evaluation in 2,282 men demonstrated high inter-session reproducibility ($r = 0.87$). This framework establishes a reproducible and population-scalable method for MRI-based assessment of penile anatomy and provides an open technical resource for future studies in urological imaging and male reproductive health. The trained model weights will be publicly released.

0

eess.IV 2026-07-03

Wave functions model images to explain low-light enhancement

by Yiquan Gao

Quantum-Inspired Vision: Leveraging Wave-Particle Duality for Low-Illumination Enhancement

Treating images as probabilistic waves integrates physics into AI for better bias handling and noise robustness.

abstract click to expand

This study provides a theoretical expansion of the recent Data Relativistic Uncertainty (DRU) framework by formalizing a physics-to-AI paradigm for image enhancement. By modeling images as probabilistic wave functions rather than deterministic states, the paradigm explicitly integrates wave-particle duality to illustrate the system flow of how DRU leverages the intrinsic physical uncertainty of light, a dimension requiring further theoretical discussion. Consequently, this paradigm provides a rigorous Explainable AI (XAI) approach that enhances the interpretability of how DRU mitigates illumination bias and maintains robustness against data noise.

1 0

0

cs.CV 2026-07-02

Enhancing three capabilities brings trackers closer to human perception

by Shih-Fang Chen

Rethinking Generic Object Tracking Toward Human-Level Perceptual Intelligence

Methods for generic object tracking target failures from deformation, distractors, and unseen categories through better discrimination, adap

abstract click to expand

At the heart of human visual perception lies the ability to maintain a continuous and coherent understanding of the external world. By integrating observations with accumulated experience, the human visual system can continuously adapt to variations in both the target and its surrounding environment, while preserving robust visual continuity as scene dynamics evolve. Human vision can therefore integrate prior knowledge, spatial geometry, and semantic context to understand complex scenes and their changes. As a core problem in computer vision, visual object tracking aims to bring machine perception closer to human visual perception. These capabilities are central to the task of Generic Object Tracking (GOT). In this task, a visual tracker is initialized only with the bounding box of an arbitrarily specified target in the first frame, and must continuously localize the target in subsequent dynamic visual streams. However, future events, observations, and real-world variations are inherently unpredictable; therefore, the model's generalization and online adaptation capabilities remain bottlenecks. Tracking reliability can deteriorate when the target undergoes severe deformation, is affected by complex distractors, encounters significant environmental changes, or belongs to a category unseen during training. This dissertation aims to narrow the gap between machine visual tracking systems and human visual perception by proposing a series of methods that systematically enhance the target discrimination, robust adaptation, and geometric reasoning capabilities of tracking models.

0

eess.IV 2026-07-02

Invariant coresets skip symmetric copies to cut active learning labels

by L. C. Ayres, J. C. M. Bermudez +2 more

Group-invariant Coresets for Data-efficient Active Learning

By selecting orbits in quotient space instead of raw samples, the method reduces wasted queries on transformed duplicates when symmetries cr

abstract click to expand

Active learning reduces labeling cost by querying the most informative unlabeled samples, but standard coreset methods ignore known data symmetries and can waste budget on transformed versions of the same instance. We propose GRINCO, a group-invariant coreset framework that performs acquisition in the quotient space induced by a transformation group, so that selection operates on orbits rather than raw samples. The method uses either canonical representatives or learned orbit-separating invariant embeddings to define practical quotient metrics, and combines quotient-space k-center selection with invariant training through an orbit-averaged loss. We further derive a generalization bound that relates excess orbit-averaged risk to quotient-space coverage, label uncertainty, and intra-orbit variability. Experiments on synthetic scale-invariant data and image benchmarks with rotation-induced redundancy show that GRINCO improves orbit coverage and achieves stronger label efficiency than conventional coreset baselines, especially when group-induced redundancy is substantial.

0

eess.IV 2026-07-02

Image tilt observations reduce UAV prediction error by 60 percent

by Minxing Sun, Yao Mao

Image-Domain Tilt Constrained Distributed Fusion for Maneuvering UAV Tracking with Multi-Camera Electro-Optical Observations

Apparent roll and pitch from rotorcraft images act as acceleration constraints in asynchronous multi-camera fusion

abstract click to expand

Short-horizon prediction is essential for electro-optical UAV tracking, especially when the target is small, maneuvering, or intermittently observed. Image center, line-of-sight, and range measurements provide direct constraints on target position, but their constraints on acceleration are weak. As a result, prediction can lag during aggressive maneuvers. This paper proposes an image-domain tilt constrained distributed fusion method for maneuvering UAV tracking. The method uses the apparent roll and pitch of a rotorcraft target in the image as low-level maneuver cues. A weak-prior auto-labeling pipeline first generates oriented bounding box and image-domain tilt labels from synchronized video, gimbal IMU, and UAV IMU data. A YOLO-OBB detector is then trained to provide online target position and tilt measurements. The front-end Python implementation is publicly available at github.com/ShineMinxing/PythonYOLO. In the fusion stage, the UAV state is modeled by position, velocity, and acceleration. Image-domain roll and pitch are introduced as acceleration-related pseudo-observations. For distributed tracking, one mobile gimbal camera and two fixed ground cameras are fused asynchronously. Camera attitude error states are augmented into the filter to absorb extrinsic drift and cross-camera systematic inconsistency. A Mahalanobis gate with time-since-last-valid covariance widening is used to reject false detections and handle dropouts. In simulation, adding roll/pitch observations reduces the prediction RMSE from 1.991 m to 0.821 m and decreases the cumulative prediction error by 60.75\%. In real distributed experiments, a self-consistency evaluation shows an 18.10\% reduction in cumulative prediction error. The results show that image-domain tilt can provide useful acceleration constraints for robust short-horizon UAV prediction.

0

eess.IV 2026-07-02

ML ensemble predicts fatal MI outcomes

by Sagnik Ghosh

Predicting Lethal Outcome (Cause) And Understanding Key Biomarkers Linked With Acute Myocardial Infarction Using Deep Artificial Neural Network And Ensemble Of Machine Learning Methodologies

Identifying key biomarkers allows faster diagnosis of deadly heart attack risks.

abstract click to expand

Cardiovascular disease is still one of the main causes of death around the world. Acute myocardial infarction (MI), or heart attack, claims millions of lives each year. MI happens when blood flow to the coronary arteries is blocked or reduced, which causes permanent damage to the heart muscle. Without treatment, this can lead to cardiac arrest, where the heart stops pumping blood to the organs, resulting in organ failure and death. Even survivors often face serious problems like heart failure, pulmonary edema, and asystole. Research shows that 5 to 10 percent of survivors die within the first year after an MI, and nearly half need to be hospitalized again. Early thrombolytic treatment leads to better outcomes, so there is a clear need for faster and more accurate ways to diagnose MI. Right now, doctors usually review patient history and use their own experience to find the causes of MI. This process takes a lot of time and can be inconsistent. Detecting MI accurately and quickly can help patients take better care of themselves and prevent fatal events. In this study, we introduce an automated model to predict deadly outcomes of MI and help doctors understand important biomarkers linked to its complications. This approach aims to make diagnosis clearer, faster, and more affordable. The process includes preparing the data, filling in missing values, and handling imbalanced data using SVMSMOTE, ADASYN, and class-weighted methods. We use wrapper and embedded feature selection to find the most important variables, then scale the features for consistency. The model combines Logistic Regression, Random Forest, Light-GBM, and Bagging SVM, and is further improved with an artificial neural network to increase accuracy. We evaluate all models using precision, recall, and other key measures to find the best option for clinical use.

0

eess.IV 2026-07-02

Watershed recovers 76% cells in malaria smears without labels

by Kaysarul Anas Apurba, Md Hasibul Hasan +2 more

MalariAI: A Label-Resilient Decoupled Framework for Universal Cell Segmentation and Explainable Stage Classification in Dense Malaria Blood Smears

Two-stage pipeline then classifies stages at 98% accuracy and supplies per-cell heatmaps for audit.

abstract click to expand

Automated malaria diagnosis from blood smear microscopy is a critical challenge in global health AI; in resource-limited settings, the scarcity of expert microscopists remains the primary bottleneck to timely and accurate diagnosis. Three compounding failure modes prevent reliable clinical deployment of existing deep learning systems. First, end-to-end detectors treat unannotated cells as background during training, producing recall figures that are strongly influenced by annotation completeness rather than reflecting true cell recovery. Second, Non-Maximum Suppression tends to suppress valid detections in dense smear regions where infection counts matter most. Third, existing whole-slide detection pipelines lack per-cell spatial evidence for clinical audit, despite image-level explainability methods such as Grad-CAM having been applied to malaria image classification tasks. We present MalariAI, a two-stage decoupled framework that addresses all three failure modes in a unified pipeline. Stage 1 applies an annotation-agnostic distance-transform guided watershed algorithm to isolate every cell in a full 1600x1200 blood smear image, recovering 75.95% of ground-truth cells by centroid localisation across the 120-image NIH BBBC041 test set without any ground-truth input. Stage 2 fine-tunes EfficientNet-B0 with Focal Loss (gamma = 2.0, per-class inverse-frequency weights) on 64x64 crops, achieving 98.36% overall classification accuracy with 87.5% and 75.0% per-class accuracy on the rare schizont and gametocyte stages, compared to only 24.57% and 25.95% AP for a Faster R-CNN baseline on the same classes. Grad-CAM++ heatmaps generated per detected cell provide instance-level spatial evidence for clinical audit, enabling microscopists to verify model predictions at the individual parasite level without sacrificing classification performance.

0

eess.IV 2026-07-02

Layer-wise feature mixup narrows prostate lesion accuracy gaps across scanners

by Josiah Simeth, Sudharsan Madhavan +8 more

Enhancing Prostate Cancer Segmentation for Multi-Domain Generalization using a novel Parallel-Route Coherent Mixup Regularization Training

PaRC-mix training on two residual networks shrinks the aggressive vs non-aggressive performance difference from ~20 to under 8 normalized po

abstract click to expand

MRI guided adaptive radiotherapy (MRgART) for prostate cancer (PCa) targets tumors while sparing organs from unnecessary radiation. Daily treatment adaptation requires accurate segmentation of tumors and organs. Manual delineation can be time and cost prohibitive. Deep learning segmentation methods have limited success applied to datasets distinct from training, hampering generalizability and adoption of MRgART. We develop a novel parallel route coherent mixup (PaRC-mix) training approach for single source to multi-domain generalization. PaRC-mix creates feature augmentations at multiple network layers through linear combination of features from different training samples in a batch. PaRC-mix training was implemented on two deep and residually connected networks, a multiple resolution residual network (MRRN) and UNet++ to segment PCa dominant intraprostatic lesions from apparent diffusion coefficient images. Models were trained on 2,029 samples from 3.0T GE MRI and tested on 1,547 PCa samples from 5 datasets acquired using 3T Siemens, 3T Philips, and 1.5T Elekta Unity MR-Linac scanners. PaRC-mix training led to significantly more accurate tumor detection and segmentation for both networks compared to training without mixup as well as input-mix training. PaRC-mix also achieved better recall to precision tradeoff than mixup applied only on the network backbone or input-mixup. Using a normalized composite DSC, HD95, and MSD score the accuracy gap between aggressive and non-aggressive lesions decreased from 21.1 and 19.5 for MRRN and UNet++ models trained without mixup to 5.2 and 7.9 with same models trained with PaRC-mix. This paper presents an easy to implement network agnostic approach to feature augmentation in multi-stream networks that enhances generalizability for the difficult problem of prostate cancer lesion segmentation.

0

eess.IV 2026-07-02

Polarimetric time-series SMI retrieves mine soil moisture at R²=0.67

by Oleg Antropov, Alireza Hamedianfar +6 more

Polarimetric SAR Model Fitting for Soil Moisture Retrieval: Study of PALSAR-2 data over a Heterogeneous Mine Environment in Finland

Sediment-calibrated generalization to [T3] matrix beats single-pol versions and matches ML benchmarks in quarry setting

abstract click to expand

This paper examines several model based approaches for retrieving surface soil moisture from ALOS-2 PALSAR-2 quad-pol imagery, over a lime stone quarry in southeastern Finland. The study primarily targets physically interpretable semi-empirical modeling approaches, with generic ML modeling used as a benchmark. Along with common polarimetric observables, we propose a generalization of the SAR time series based TU Wien soil moisture index (SMI) retrievals examined across several representational spaces derived from polarimetric coherency matrix $[T3]$. This study was conducted over a closed tailing storage facility and a landfill, with a set of 9 repeat pass PALSAR-2 images. The best semi-empirical configuration combining temporal context SMI and current observation PolSAR parameters achieved $R^2=0.67$ and RMSE $=5.65$ volumetric \% units. The strongest $SMI_{[T3]}$ approach with sediment-specific calibration, achieved $R^2=0.66$ and RMSE $=5.67$ vol. \%, which was considerably better than using $SMI_{HH}$ or $SMI_{VV}$. The proposed approach was sensitive to representations: dB-based projection outperformed linear or trace-normalized $[T3]$ representation. Factoring in sediment information dramatically improved retrieval performance compared to using global model fitting. Machine learning results closely approached but not outperformed semi-empirical model based methodologies. Similarly, they highlighted the need for sediment-specific modeling as well as the importance of including time-series/temporal backscatter dynamics during SSM retrieval. Our study demonstrated the utility of physics based SSM retrieval approaches in the complex multi-sediment mine environment under relatively scarce reference data conditions.

0

eess.IV 2026-07-01

Joint k-space model corrects EPI distortions better at high b-value

by Wenqi Huang, Zhitao Li +9 more

Distortion-Corrected Diffusion MRI Using Rotated-View EPI and Joint Field-Map/Image Estimation with Gaussian Primitives

Gaussian-primitive representation of field and image from raw data outperforms sequential correction on brain diffusion scans.

abstract click to expand

Echo Planar Imaging (EPI) is the standard acquisition technique for diffusion and functional neuroimaging, enabling rapid imaging but suffering from geometric distortions caused by B0 field inhomogeneities. Existing correction methods first reconstruct distorted images using parallel imaging, then estimate the B0 field and correct the distortion in the image domain. In this sequential process, reconstruction artifacts at high acceleration factors and low SNR at high diffusion b-values degrade B0 estimation and limit the overall correction quality. We propose a physics-informed framework that jointly estimates the B0 field and distortion-free image directly from k-space data, without depending on an intermediate parallel-imaging reconstruction for the correction. The image and the B0 field are each represented as a superposition of Gaussian primitives embedded within an MRI physics forward model. The explicit, continuous parameterization captures both smooth regions and tissue boundaries and supports rotated-view EPI acquisitions without interpolation. The diffusion-weighted image is modeled as real and non-negative, with the image phase absorbed into a per-shot phase factor. Rotated views distribute distortions across multiple phase-encoding orientations, improving point spread function isotropy and providing stronger constraints for B0 estimation. On in vivo brain diffusion EPI, the proposed method attains the closest brain-boundary agreement with a distortion-free structural reference, with the largest improvement over sequential methods at high b-value and high acceleration. Extensive visual comparisons further show improved detail fidelity and noise suppression.

0

eess.IV 2026-07-01

2-tap filter approx cuts MMVD search ratio in half

by Xinmin Feng, Shengyang Xu +4 more

Accelerating Merge with Motion Vector Difference via Filter Difference Analysis for VVenC

Approximating the 8-tap interpolation filter with a 2-tap version yields a cheap test that safely rejects most Merge with Motion Vector Diff

abstract click to expand

Merge with Motion Vector Difference (MMVD) is a key coding tool in Versatile Video Coding for improving motion prediction accuracy. However, its exhaustive search strategy imposes a significant computational burden on the encoder. To address this issue, we propose a novel fast MMVD algorithm for the VVenC encoder based on fractional motion vector filter difference analysis. By approximating the 8-tap interpolation filter with a 2-tap filter, we derive a criterion based on spatial gradients and prediction residuals for estimating the potential gain of MMVD candidates. We further generalize this criterion to accommodate both shifted integer reference samples and 2D separable filtering. To minimize the overhead of the proposed method, we introduce implementation optimizations, including symmetric offset inference and cross-shaped downsampled dot-product computation. Compared with existing fast MMVD algorithms in VVenC, our method reduces the average MMVD search ratio from 21.07\% to 11.05\% and decreases the efficiency-complexity metric $\eta$ from 11.79 to 7.10 under the fast preset.

0

cs.CV 2026-06-30

Point seeds deliver state-of-the-art multi-object tracking

by Kai Luo, Fei Teng +7 more

PS-MOT: Cultivating Instance Awareness from Point Seeds for Multi-Object Tracking

A three-stage pipeline turns center points into full trackers without bounding-box labels on dance, sports, and robotics videos.

abstract click to expand

We introduce Point-supervised Multi-Object Tracking (PS-MOT) as a cost-effective alternative to traditional bounding box supervision, shifting the focus from spatial fitting to topological center-driven representation. However, PS-MOT faces challenges, e.g., spatial ambiguity and identity drift due to the lack of explicit geometric structure and scale constraints. To address these, we propose PS-Track, a hierarchical pipeline transitioning from points to instances across data, model, and loss levels. At the data level, we introduce Temporal-Feedback Prompting (TFP) to evolve points into temporally consistent pseudo-labels using negative spatial cues and motion priors. At the model level, we design the Point-Excited Wavelet Attention (PEWA) module, which leverages semantic correlations to activate high-frequency components, ``hallucinating'' object boundaries. At the loss level, Uncertainty-Guided Gaussian Learning (UGL) models pseudo-labels as probabilistic distributions, dynamically calibrating supervision intensity. Experiments on DanceTrack, EmboTrack, SportsMOT, and JRDB demonstrate that PS-Track provides a feasible and effective point-supervised alternative across diverse tracking scenarios, establishing a new state-of-the-art for point-supervised tracking. The source code is available at https://github.com/xifen523/PS-MOT.

0

cs.CV 2026-06-30

Cascaded vision pipeline reads resistor values from photos at 85.8% accuracy

by Rama Y. AlHamidi, Aseel A. Mohamed +3 more

HiRes: A Hierarchical Cascaded Method for Resistor Value Identification

Detection and segmentation followed by geometric projection handles real-world conditions where classical tools fail.

abstract click to expand

Accurate identification of resistor values from unconstrained images remains a challenging computer vision task due to variations in lighting, orientation, scale, and background complexity. This paper presents HiRes, a hierarchical cascaded pipeline for end-to-end resistor value identification directly from full-frame images. The approach combines object detection (YOLOv8n), semantic segmentation (UNet++ with EfficientNet-B2), and structured geometric decoding via projection along the resistor axis. To improve robustness, we incorporate geometric filtering, gap-preserving band separation, and validation against the E24 resistor series. Experiments across diverse real-world images show that HiRes achieves a detection mAP50 of 0.9906, a segmentation mIoU of 0.8444, and an end-to-end identification accuracy of 85.8% (95% CI: 78.0-91.9%), outperforming the publicly available classical baseline, CVResist, which fails to generalize beyond controlled conditions. In addition, our architecture outperforms state-of-the-art MLLMs on our challenging test set, offering a lower cost, high efficiency, and an interpretable alternative method. These results demonstrate the effectiveness of integrating learned visual representations with structured reasoning for robust resistor interpretation. Code and dataset are available at https://github.com/HiRes491/HiRes.

0

cs.CV 2026-06-30

Cylindrical model keeps object IDs stable across 360-degree seams

by Buyin Deng, Kai Luo +6 more

CylindTrack: Depth-Aware Cylindrical Motion Modeling for Panoramic Multi-Object Tracking

Depth is filtered at the trajectory level and motion is predicted in angular space so associations survive the periodic boundary and scale c

abstract click to expand

Multi-Object Tracking (MOT) is a core capability for embodied perception, and panoramic cameras are attractive for embodied systems because their 360{\deg} field of view reduces blind spots and keeps surrounding targets observable for longer durations. However, panoramic MOT is not a straightforward extension of perspective MOT. In equirectangular panoramic videos, the horizontal image domain is periodic rather than Euclidean, which breaks planar motion assumptions and makes IoU-based association unreliable near the 0{\deg}/360{\deg} seam. Meanwhile, large-FoV scenes often contain more objects, stronger scale variation, and more frequent interactions, making online association particularly sensitive to unstable frame-wise depth cues. To address these issues, we propose CylindTrack, a depth-aware cylindrical tracking-by-detection framework for panoramic MOT. CylindTrack first introduces Depth-Temporal Trajectory Modeling (DTM), which promotes instance depth from an isolated frame-wise cue to a temporally filtered trajectory-level state. To improve the reliability of depth observations, we further develop Spherical Spatio-Temporal Consistency Learning (SSTC), which combines a Temporal Mixer and Spherical Geometry-aware Attention to enhance temporal coherence and panoramic geometric alignment in depth-aware representations. Finally, we design a Topology-Aware Cylindrical Motion Model (TCMM) that lifts horizontal motion into a continuous angular state space and performs seam-consistent motion prediction and association in the periodic panoramic domain. By jointly modeling trajectory-level depth consistency and panoramic topology, CylindTrack improves identity preservation and trajectory continuity in challenging panoramic scenes. The source code will be released at https://github.com/warriordby/CylindTrack.

0

eess.IV 2026-06-30

Prostate MRI false positives match cancer contrast across models

by Yongbo Shu, Kewen Chen +6 more

A multi-architecture study of specificity refinement and false-positive mechanism analysis in prostate MRI

Residual errors share raw T2 and ADC features with true lesions rather than arising from model-specific flaws; lightweight refinement raises

abstract click to expand

Objectives: To characterize residual false positives in prostate MRI detection, and to evaluate a lightweight post-hoc refinement head for case-level specificity. Materials and Methods: This retrospective study used PI-CAI (5-fold cross-validation) and Prostate158 (n=158; external). A context-aware evidence head and an 89,216-parameter refinement head were trained on a frozen detection backbone; the evidence head was also trained on four further backbones (bare nnU-Net, bare U-Net, bare Mamba, MIGF-Mamba). For each false-positive region, T2-weighted, apparent-diffusion-coefficient, and high-b-value contrast ratios versus peri-lesional rings were compared against ground-truth lesions and contralateral benign regions. Results: False positives were closer to true cancers than to benign tissue in evidence and raw T2-weighted and apparent-diffusion-coefficient contrast, reproducing 35/35 across five architectures (Cohen's d 1.10; FP/benign evidence ratio 2.38x) and 105/105 across modality-perturbation scenarios. On PI-CAI fold-0, refinement raised case-level specificity from 0.469 to 0.549 (+17.2%) at preserved sensitivity (0.943); 5-fold cross-validation showed fold-conditional behavior (9/15 observations positive; range -22% to +28%). On Prostate158, both models saturated (McNemar pooled p=0.69), while the false-positive contrast-matching finding replicated. Conclusion: Residual false positives are contrast-matched to cancer (sharing raw imaging features rather than histologically confirmed mimicry), reproducing across five architectures -- a data-level imaging property, not model-specific artifacts; post-hoc refinement adds practical specificity in-domain but is fold-conditional.

0

eess.IV 2026-06-30

Lightweight module turns H&E slides into molecular pathway predictors

by Dominik Winter, Dominik Vonficht +7 more

Data-Efficient Multimodal Alignment for Histopathology-based Molecular Prediction

Contrastive training on 1720 samples aligns frozen models for 25-fold better gene-set retrieval without new sequencing.

abstract click to expand

H&E-stained whole-slide images offer cohort-scale availability and rich spatial context but lack molecular specificity, whereas bulk RNA-seq provides transcriptome-wide resolution at high cost with limited archival availability. We show that training a lightweight alignment module atop frozen histopathology and RNA-Seq foundation models enables open-vocabulary molecular prompting -- querying H&E slides with gene-set signatures to predict pathway activity without sequencing or end-to-end retraining. Using contrastive learning on a multi-cancer cohort (N=1,720), we achieve a 25-fold improvement in retrieval over baseline methods. Systematic analysis reveals a graduated predictability spectrum: morphologically grounded programs (cell-cycle programs, immune-related) are most reliably predicted (R^2>0.5), while predicting pathways with no morphological footprint remains challenging as expected. We validate clinical utility on the POSEIDON clinical trial: H&E-predicted squamous cell carcinoma scores recapitulate NSCLC subtype identity and predicted IFN-gamma mirror PD-L1 tumor-cell expression groups. Furthermore, genesets describing immune activation and fibrosis predict known tumor microenvironment archetypes from histology alone. We further validate generalization of our approach across unseen cohorts and demonstrate data-efficient domain adaptation, establishing a slide-native framework for molecular analysis on H&E images.

0

eess.IV 2026-06-29

4-way split encoding hits 122 fps real-time for 8K V-PCC on Blackwell GPUs

by Kasidis Arunruangsirilert, Jiro Katto

Performance Analysis of Hardware-Accelerated 10-Bit 4:2:2 Encoding with Split-Frame Encoding for High-Fidelity V-PCC Streaming

Standard GPUs now support the 10-bit 4:2:2 demands of high-density volumetric streaming without custom chips.

abstract click to expand

Video-based Point Cloud Compression (V-PCC) encodes volumetric data by projecting 3D geometry and texture onto 2D video frames. To prevent spatial distortion and color bleeding during 3D reconstruction, this process requires 10-bit color depth and 4:2:2 chroma subsampling, rather than the standard 8-bit 4:2:0 format. Additionally, capturing high-density dynamic point clouds requires demanding encoding parameters, such as 8K resolution at framerates up to 120 fps. Historically, the lack of 4:2:2 chroma support in older GPU hardware encoders restricted real-time V-PCC to custom Application-Specific Integrated Circuits (ASICs). However, the recent introduction of NVIDIA's Blackwell GPU architecture, featuring on-chip hardware encoders with 10-bit 4:2:2 support, presents an opportunity to shift this workload to general-purpose hardware. This paper investigates the feasibility of such an approach. Using a commercially available Blackwell GPU equipped with four parallel on-die hardware encoders as a testbed, we evaluate the throughput, rate-distortion (RD) performance, and power consumption of 8K 10-bit 4:2:2 HEVC across various Split-Frame Encoding (SFE) configurations. Our results demonstrate that 4-way SFE achieves an encoding throughput of 122 fps, successfully meeting the strict real-time constraints of high-density V-PCC. Although the inability to exploit spatial redundancies across slice boundaries results in a BD-Rate penalty of up to 5%, the measured throughput and power efficiency establish standard, commercial off-the-shelf GPUs as a highly viable baseline for real-time volumetric video streaming.

1 0

0

eess.IV 2026-06-29

Compression response clusters videos for bitrate savings

by Krishna Srikar Durbha, Hassene Tmar +3 more

A Self-Supervised Learning Framework for Video Encoding Complexity Clustering

Self-supervised method groups content by how it reacts to compression, enabling content-aware encoding ladders that cut data use and raise q

abstract click to expand

Adaptive video streaming is a widely used technique for delivering video content over the internet. One of the key challenges is determining the optimal encoding settings for each video, which can vary significantly based on its content and characteristics. In this paper, we propose Compression Echo Contrastive Learning (CECL), a novel self-supervised learning framework for clustering videos based on their encoding complexity. Our method leverages the response of a video to compression - the Compression Echo - as a supervisory signal, allowing the model to capture underlying encoding characteristics during pretraining. We conduct extensive experiments to demonstrate the effectiveness of our learned representations for the downstream task of clustering videos by their encoding complexity. Our results show that CECL improves upon existing state-of-the-art visual encoders and delivers strong bitrate and quality savings against the fixed bitrate ladder.

0

cs.CV 2026-06-29

Localized pretraining improves detection of area-specific image distortions

by Krishna Srikar Durbha, Hassene Tmar +3 more

Spatially Localized Image Degradation Embeddings for Image Quality Assessment

SLIDE-IQA adds bounded synthetic degradations to contrastive training so models notice partial-frame problems while staying competitive on f

abstract click to expand

Self-supervised learning (SSL) currently drives state-of-the-art performance in no-reference image quality assessment (NR-IQA). However, standard SSL pipelines uniformly apply synthetic distortions across the entire image field, which can limit their sensitivity to spatially localized and co-occurring degradations encountered in real-world content. In this work, we empirically expose this representational blind spot across existing state-of-the-art encoders, demonstrating their reduced sensitivity to spatially bounded image degradations. To bridge this gap, we introduce Spatial Localized Image Degradation Embeddings for Image Quality Assessment (SLIDE-IQA). SLIDE-IQA employs a dual-branch Vision Transformer framework that injects spatially bounded degradations into a contrastive pretraining objective. To handle the spatial complexity of these degradations, we introduce a Threshold-Bounded Exclusion Mechanism, a representational design choice that resolves structural conflicts arising from spatially localized distortions to ensure the latent space respects both degradation type and spatial scale. Finally, we show that SLIDE-IQA's synthetic-only pretraining significantly improves sensitivity to localized distortions, while achieving competitive performance on NR-IQA benchmarks against existing SSL NR-IQA models.

0

eess.IV 2026-06-29

First complete virtual reading of Herculaneum scroll

by Giorgio Angelotti, Stephen Parsons +25 more

Complete virtual unwrapping and reading of a rolled Herculaneum papyrus

X-ray microtomography and refined algorithms recover full text from unopened ancient papyrus without damage.

abstract click to expand

The carbonized papyri from Herculaneum preserve the only large-scale library to survive from classical antiquity, but many unopened rolls remain unread because physical opening risks irreversible damage. X-ray computed microtomography ($\mu$CT) and virtual unwrapping offer a non-invasive route to their texts, yet previous work on sealed Herculaneum scrolls has recovered only localized readings or limited surface regions. Here, using high-resolution phase-contrast $\mu$CT acquired on the BM18 beamline at the European Synchrotron Radiation Facility (ESRF), together with improved computational unrolling and machine learning, we achieve the complete virtual unwrapping and reading of PHerc. 1667 under explicit coverage and papyrological-review criteria. This makes PHerc. 1667 the first Herculaneum papyrus to be fully digitally unrolled and read for extended scholarly study without physical opening. In PHerc. Paris 4, the optimized scan protocol makes ink directly visible in the tomographic volume, allowing three-dimensional ink segmentation and independent validation of surface-conditioned ink recovery. In PHerc. 139, we recover title and author-attribution evidence identifying the scroll as Philodemus, On Gods, Book 8. These results move virtual unwrapping of the Herculaneum scrolls beyond isolated demonstrations towards a scalable framework for systematic recovery of the still-unopened library.

0

cs.CV 2026-06-29

Metadata turns routine scan details into pre-training signal for cardiac MRI

by Xueyi Fu, Liwei Hu +2 more

Learning from Acquisition: Metadata-driven Multimodal Pre-training for Cardiac MRI

A CLIP-style model using acquisition metadata matches large image-only pre-training on segmentation while needing under 1 percent as many im

abstract click to expand

Cardiac magnetic resonance imaging (CMR) routinely records structured acquisition metadata, yet most CMR foundation models rely primarily on image-only pre-training and leave this naturally available source of weak semantic supervision largely underexplored. We propose MetaCLIP-CMR, a metadata-driven framework based on Contrastive Language--Image Pre-training (CLIP), which converts imaging modality, anatomical view, scanner vendor, field strength, and scanner model into textual supervision for CMR representation learning. The pretrained image encoder is evaluated on imaging modality classification, cine view classification, and cardiac segmentation. MetaCLIP-CMR achieves 86.8% modality accuracy and 86.5% cine view accuracy, clearly outperforming ImageNet and masked reconstruction initialisations. For downstream cardiac segmentation, MetaCLIP-CMR consistently obtains the highest Dice score across the evaluated ACDC and M&Ms cine short-axis (SAX) settings under both full-data and 20% fine-tuning regimes. Compared with recent image-focused large-scale CMR pre-training models, MetaCLIP-CMR achieves comparable ACDC segmentation performance, while requiring less than 1% of their pre-training image scale. These results suggest that metadata learning offers a natural and easy-to-use strategy for transforming routinely recorded acquisition information into effective supervision for foundation-level CMR representation learning, highlighting the promise of metadata-driven multimodal pre-training.

0

eess.IV 2026-06-29

Diffusion model tailors SAR data to new sensors

by Xuanting Wu, Fan Zhang +3 more

Cross-Sensor SAR Data Generation Using Diffusion Models and Feature Migration

Attention distillation migrates texture and speckle features from historical records to match new satellite imaging traits.

abstract click to expand

Different synthetic aperture radar (SAR) sensors vary significantly in resolution, polarization modes, and frequency bands, making it difficult to directly apply existing models to newly launched SAR satellites. These new systems require large amounts of labeled data for model retraining, but collecting sufficient data in a short time is often infeasible. To address this contradiction, this paper proposes a data generation and transfer framework, integrating a stable diffusion model with attention distillation, that leverages historical SAR data to synthesize training data tailored to the unique characteristics of new SAR systems. Specifically, we fine-tune the low-rank adaptation (LoRA) modules within the multimodal diffusion transformer (MM-DiT) architecture to enable class-controllable SAR image generation guided by textual prompts. To ensure that the generated images reflect the statistical properties and imaging characteristics of the target SAR system, we further introduce an attention distillation mechanism that transfers sensor-specific features, such as spatial texture, speckle distribution, and structural patterns, from real target-domain data to the generative model. Extensive experiments on multi-class aircraft target datasets from two real spaceborne SAR systems demonstrate the effectiveness of the proposed approach in alleviating data scarcity and supporting cross-sensor remote sensing applications.

0

eess.IV 2026-06-29

Agent framework turns text requests into validated SAR augmentations

by Xuanting Wu, Fan Zhanga +4 more

A Task-Driven and Quality-Assured Agent Framework for SAR Data Generation

SAGA extracts facts, constrains planning with validators, and qualifies samples via multiple evaluators to raise downstream task performance

abstract click to expand

Synthetic aperture radar (SAR) data augmentation is important for improving the generalization of data-driven SAR interpretation models, yet practical augmentation workflows are often hindered by heterogeneous dataset formats, task-dependent metadata requirements, diverse generation methods, and weak validation of generated samples. This paper presents the \textbf{S}AR \textbf{A}ugmentation and \textbf{G}eneration \textbf{A}gent (SAGA), a schema-grounded and benefit-aware agent framework for task-oriented SAR data generation and augmentation. Given a natural-language request and heterogeneous SAR inputs, SAGA extracts observable dataset facts, validates executable dataset schemas, selects feasible augmentation strategies through validator-constrained planning, and compiles the selected strategy into an auditable augmentation workflow. Generated data are further assessed by quality, distribution, SAR-artifact, duplicate, leakage, and optional downstream-task evaluators to support evidence-qualified augmentation claims. By separating semantic proposal from deterministic validation and execution, SAGA improves the reliability and reproducibility of SAR augmentation decisions. Experiments on controlled agentic benchmarks and downstream SAR interpretation tasks show that SAGA improves schema grounding, skill planning, invalid-sample rejection, and downstream augmentation utility compared with rule-based, LLM-only, ReAct-style, and fixed-augmentation baselines.

0

eess.IV 2026-06-29

Seed-frame swap cuts surveillance video size by 35 percent

by Shubham Baid, Akash James +3 more

BLUE: A Stale-Pixel Optical-Flow Compositor for Entropy-Efficient Surveillance Video Encoding

Compositor freezes static background pixels before encoding so codecs skip re-encoding them while keeping moving objects at full quality.

abstract click to expand

Continuous-recording surveillance systems face a storage problem that codec tuning alone cannot fully solve: even at aggressive CRF settings, a static-camera scene spends most of its bits re-encoding a background that has not changed. We present BLUE, a pre-encode compositor that exploits this structure by maintaining a persistent seed frame of the background and substituting background pixels with seed pixels before the encoder runs. The encoder then emits near-free SKIP macroblocks for the frozen background, while live pixels in foreground regions are carried unchanged at full quality. We evaluate BLUE on all 308 annotated short subclips from the VIRAT Ground Surveillance Release 2.0 dataset using a six-point CRF sweep with both x264 and x265. At CRF 28, BLUE reduces file size by a mean of 34.6% (x264) / 39.4% (x265) on 95.8% / 99.4% of clips respectively. Foreground-region PSNR, computed only over VIRAT object-annotation bounding boxes, is preserved or improved on 60.7% of clips (+0.36 dB mean, +5.48 dB maximum). Full-frame perceptual quality (VMAF) drops by a median of 6.75-8.59 points; we quantify and disclose this trade-off explicitly. A lightweight deployment gate measuring the compositor's own VMAF on a 2-second prefix identifies the 40% of clips where even full-frame quality degradation is near-imperceptible (Delta VMAF <= -2.9), enabling a selective-activation strategy that retains both the storage benefit and acceptable perceptual fidelity.

0

eess.IV 2026-06-29

Framework supplies ground-truth causal data for brain-image AI

by Eryn Libert-Scott, Emma A.M. Stanley +4 more

A Neuroimaging Simulation Framework for Developing and Evaluating Causal AI

Targeted volume edits create realistic 3D scans whose known causal links can benchmark discovery algorithms.

abstract click to expand

Causally linking disease-related factors to image-derived biomarkers provides a powerful pathway to understanding disease mechanisms. Despite growing interest in applying causal artificial intelligence (AI) approaches for this task, these methods still need to be adapted for complex medical images, and especially, neuroimaging. However, the lack of ground-truth data presents a barrier to development. To bridge this gap, we developed and tested a method for generating synthetic neuroimages, which adhere to a user-specified causal structure describing the non-image to image variable relationships, permitting the creation of ground-truth neuroimaging datasets. In the simulated T1-weighted magnetic resonance images, anatomical variability is modeled by sampling from a subspace estimated from real data and deforming a template image to create unique simulated subjects. Causal relationships are encoded via precise volumetric changes of any region-of-interest without unwanted global artifacts. We achieved relative volume errors of 0.3-2.66% for the targeted regions-of-interest and demonstrate their statistically significant causal relationships, while maintaining mean absolute errors for non-target brain regions between 0.034-0.397ml. An initial evaluation of causal discovery methods exposes their limited ability to suppress spurious connections, highlighting the need for image-appropriate methods. Our framework is the first to enable the generation of realistic synthetic 3D neuroimages with explicit causal control that can serve as the missing ground-truth data necessary for the objective benchmarking and development of causal AI methods.

0

eess.IV 2026-06-29

Mask-decomposed score ranks rhinoplasty edits where identity metrics fail

by Mudit Agarwal, Amit D. Bhrany

Envisage: Diffusion-Based Rhinoplasty Goal Visualization with Mask-Decomposed Evaluation

Full-face ArcFace gains stay negative for all methods because unchanged pixels dominate the score; SurgicalScore isolates the edited region.

abstract click to expand

Localized generative editing needs localized evaluation: full-image identity metrics are structurally confounded under hard-composited edits. We present Envisage, a FLUX.1-Fill inpainting reference pipeline for rhinoplasty goal visualization from a single frontal photograph. The pipeline combines 8 rhinoplasty clinical presets (the released framework also includes 8 blepharoplasty and 8 rhytidectomy presets), MediaPipe masks, and hard-mask compositing. The composite preserves outside-mask pixels by construction, so full-face identity scores are dominated by copied pixels rather than by the diffusion backbone. Because full-face identity metrics cannot grade localized edits, we introduce SurgicalScore, a mask-decomposed 0-1 protocol scoring edit direction, edit magnitude, masked LPIPS, realism, and outside-mask preservation; SS_raw assigns 0.919 [0.918, 0.920] to a perfect-predictor control , anchoring the ceiling. On N=211, the paired ArcFace gain (output-to-GT minus input-to-GT) is negative for all methods (Envisage -0.048 smallest, vs. ICEdit -0.139, Kontext -0.242, InstructPix2Pix -0.294; p < 1e-4), with external validation on a 457-pair ASPS/PCA corpus showing a larger negative gap. With SurgicalScore, Envisage achieves the highest score (0.599 [0.579, 0.619]) and leads on both metrics, but the all-negative ArcFace gap shows that full-face identity is poorly aligned with localized surgical accuracy under hard compositing. A 5-seed GT-oracle (an upper bound, not a deployable result) reduces the residual ArcFace gap by 73% (-0.054 to -0.015), with positive output-to-GT gain on 33.9% of cases, indicating candidate-space headroom for a learned ranker. For localized edits, progress should be measured with edit-region fidelity rather than full-face identity metrics. We release Envisage, SurgicalScore, preset definitions, and matched split manifests.

0

eess.IV 2026-06-29

Activity-aware noise in diffusion model improves low-count PET accuracy

by Raymond Confidence, Udunna C. Anazodo

HDDPM: Heteroscedastic Denoising Diffusion Probabilistic Model for Quantitative Low-Count Brain PET Recovery

Poisson variance maps place stronger corruption on low-activity regions, cutting quantitative errors especially at 1% dose across scanners.

abstract click to expand

Positron emission tomography (PET) seeks to balance diagnostic quality with ra-diation dose. Low-count PET noise is non-Gaussian, non-stationary, and spatial-ly dependent. It scales directly with local activity and is shaped by iterative recon-struction and physical corrections. Standard denoising diffusion probabilistic models (DDPMs) ignore these PET properties. Their forward process adds iso-tropic, homoscedastic Gaussian noise to the target. Such an approach fails to cap-ture the realistic physical degradation generated by the imaging system. To ad-dress the above limitations, this study introduces a heteroscedastic residual diffu-sion model (HDDPM) for low-count brain PET recovery in which the forward corruption is itself intensity-aware. We designed a fixed, Poisson-based variance module to generate voxel-wise noise maps. These maps naturally place stronger noise perturbation on low-activity regions than high-activity ones, meanwhile the network predicts the low-to-standard-count residual under explicit dose-fraction conditioning. We evaluated our proposed model (HDDPM) alongside generative frameworks across three different scanners, using both internal and external da-tasets at various simulated dose levels (1% to 50%). HDDPM and isotropic DDPM showed comparable overall image quality, but HDDPM stood out in the lowest-dose (1%) external scans. It is highly reliable and significantly reduces measurement errors in both high- and low-activity regions, compared to the standard model. These results support that heteroscedastic noising with the pro-posed HDDPM is feasible, and it provides a physically motivated inductive bias for quantitative low-count PET recovery by reflecting the activity-dependent noise structure of PET.

0

eess.IV 2026-06-29

Synthetic angiograms from CT scans label coronary views without humans

by In Kyu Lee, Sumin Seo +1 more

Anatomy-Grounded Synthetic Coronary Angiography for Geometry-Informed Multi-View Matching

Dense 3D-to-2D projection labels from simulated C-arm geometry train geometry-informed matching models for better 3D reconstruction.

abstract click to expand

Accurate correspondence matching across multiple angiographic views is the prerequisite for 3D coronary reconstruction and interventional guidance. However, the development of robust deep learning models for this task has been stifled by a fundamental data bottleneck. Obtaining ground truth for matching tasks in angiography pairs is prohibitively expensive and hard to scale. To overcome this barrier, we introduce a physically-grounded data generation framework that synthesizes high-fidelity Digital Reconstructed Radiographs (DRRs) from 3D Coronary CT Angiography (CCTA) volumes. Our framework generates dense, highly accurate 3D-to-2D projection labels by simulating realistic C-arm acquisition geometry on patient anatomy at zero human cost. Leveraging this dense supervision, we propose a Geometry-Informed Matching Module (GIMM) that integrates global feature and anatomical structure into correspondence learning. Unlike real angiography where assessment relies on subjective human annotation, our dataset provides 2D correspondence labels with paired images, allowing human-free evaluation. We comprehensively evaluate our method on the proposed CT-derived DRR dataset and demonstrate improvements over other matching baseline models.

0

eess.IV 2026-06-29

New INR codec holds complexity fixed across four levels

by Ho Man Kwan, Tianhao Peng +4 more

Enhanced Neural Video Representation Compression across Extreme Complexity and Quality Scales

NVRC++ spans wide bitrates and qualities at each level while decoding up to 7.6 times faster than prior INR methods.

abstract click to expand

Implicit neural representations (INRs) have recently emerged as a promising approach to video compression, delivering competitive rate-distortion performance alongside rapid decoding. However, existing neural video codecs struggle to balance complexity and scalability. Lightweight models often suffer from degraded compression performance when scaled to different bitrate/quality levels, whereas high-performance models exhibit limited scalability, as their model complexity typically increases with quality. This lack of a unified architecture capable of maintaining consistent complexity across a wide range of bitrates severely limits their diverse real-world deployment. To address these challenges, we introduce NVRC++, a novel INR-based video codec that utilizes a lightweight INR with multiple high-resolution feature grids, providing high scalability at any given complexity level. This is paired with an optimization framework that enables efficient overfitting on high-resolution grids for long video sequences, thereby exploiting spatio-temporal redundancies without prohibitive computational or memory overhead. Additionally, an advanced entropy model is designed for efficiently compressing the high-dimensional grid parameters. As a result, NVRC++ provides four complexity levels (from 7kMACs/pixel to 360kMACs/pixel), each spanning wide bitrate and quality ranges while supporting real-time decoding. The experimental results show that NVRC++ offers a much faster decoding speed (up to 7.6x) compared to the SOTA INR-based video codec, NVRC, while delivering comparable performance.

0

cs.LG 2026-06-29

Neural nets recover conductivity maps from boundary data

by Ali AlHadi Kalout, Pablo Tejerina-Pérez +6 more

Recovering Sharp Conductivity Features in the Finite-Data Calder\'on Problem with Physics-Informed Neural Networks

A PINN framework with wavelet excitations and Fourier encodings achieves 3-12% error on sharp features in the finite-data Calderón problem.

abstract click to expand

Physics-informed neural networks (PINNs) have recently emerged as a promising framework for addressing the Calder\'on inverse problem from limited boundary data. In this work, we revisit neural Calder\'on inversion by introducing multiscale boundary excitations based on randomized wavelet functions and investigating the role of Fourier-feature encoding (FFE) for representing sharp conductivity variations. We propose a physics-informed reconstruction framework that represents the unknown conductivity and the associated family of electric potentials with separate neural networks conditioned on the applied boundary excitations. The governing elliptic PDE is enforced through physics-informed residuals, while finite Dirichlet-to-Neumann (DtN) data are incorporated through boundary losses. Using synthetic data from a finite-difference forward solver, we evaluate the method on conductivity fields with inclusions, sharp interfaces, smooth profiles, and heterogeneous media. Results show that the framework recovers dominant conductivity structures from finite boundary measurements with relative errors between $3\%-12\%$ approximately. We show that FFE improves the reconstruction of localized sharp features, particularly for inclusions and interfaces, but are not universally optimal, with raw-coordinate networks performing competitively for smoother fields. These results highlight coordinate representations and boundary excitation design as key factors in neural Calder\'on inversion.

0

eess.IV 2026-06-29

Explicit scale parameters make neural video codec work on any device

by Tanel Pärnamaa, Martin Lumiste +4 more

MLVC: Multi-platform Learned Video Codec for Real-World Deployment

Transmitting scales through the hyperprior removes hardware decoding mismatches while delivering 70 percent better rate than HEVC at 100 FPS

abstract click to expand

Neural video codecs have surpassed classical codecs in coding efficiency but remain impractical for deployment due to cross-platform incompatibility and high computational cost. Existing quantization-based solutions fail to produce deterministic results across diverse hardware platforms, leading to catastrophic decoding failures. We introduce MLVC, a hardware-robust neural video codec designed for practical cross-platform inference. The key idea is to explicitly transmit scale parameters through the hyperprior, which guarantees entropy coding consistency across devices without requiring bit-exact arithmetic. While this increases bitrate overhead, we recover most of the coding efficiency through architectural improvements (gated memory, ReGLU activation), a long-term reference recovery mechanism, and domain-specific perceptual training. On the VCD video conferencing benchmark, MLVC achieves >70% BD-rate (MOS) improvement over hardware HEVC, the strongest deployable baseline, while reaching subjective quality competitive with DCVC-RT, which cannot operate across diverse platforms. Both the encoder and decoder run at 100 FPS on average on commodity NPUs from Apple, Intel, and Qualcomm. MLVC is the first neural video codec to combine competitive compression performance, real-time speed, and cross-platform robustness across diverse consumer devices, making it suitable for widespread deployment. Code will be released.

0

eess.IV 2026-06-29

Autoregressive model improves low-dose CT image denoising

by Xizhuo Zhang, Yannian Gu +3 more

DeVAR: Low-Dose CT Denoising via Visual Autoregressive Modeling

DeVAR generates NDCT from LDCT tokens with scale prediction and residual refinement for better detail preservation.

abstract click to expand

Computed tomography (CT) plays a crucial role in medical diagnosis, but minimizing radiation exposure while maintaining image quality remains a critical challenge. Low-dose CT (LDCT) protocols reduce radiation risks but inevitably suffer from severe noise and artifacts that compromise diagnostic accuracy. While existing deep learning methods have achieved promising results, there remains a continuous quest for generative paradigms that intrinsically capture global-to-local structural dependencies to better preserve fine anatomical details. To this end, we propose DeVAR, a novel generative framework that applies visual autoregressive modeling (VAR) to LDCT denoising for the first time. Conditioned on global context provided by LDCT prefix tokens, DeVAR progressively generates discrete token maps of the target normal-dose CT (NDCT) via next-scale prediction. Because quantization inherently discards high-frequency information, we introduce a residual refiner to capture subtle anatomical structures beyond the capacity of a discrete codebook. Finally, empowered by a dual-representation hybrid training strategy, our hybrid NDCT decoder seamlessly integrates continuous and discrete latents to reconstruct high-fidelity, detail-preserved images. Extensive experiments on two public datasets demonstrate that DeVAR consistently achieves superior qualitative and quantitative performance compared to state-of-the-art LDCT denoising methods.

0

eess.IV 2026-06-29

Consistency lock confines MRI diffusion samples to null space

by Junhyeok Lee, Kyu Sung Choi

Measured-Subspace Consistency: A Plug-and-Play Operator for Diffusion Posterior Sampling in Accelerated MRI Reconstruction

MSC wraps any sampler with a standard multi-coil step, cutting measured k-space disagreement up to 29 times while keeping unmeasured diversi

abstract click to expand

Diffusion posterior samplers for accelerated MRI can reconstruct accurately yet still disagree on the acquired k-space across samples, placing posterior variability on coefficients the scanner has already measured. We identify this measured-subspace leakage as a physical-admissibility failure. Under a hard-constraint model it violates the measurement constraint and inflates the reported uncertainty with disagreement about coefficients the scanner has already determined. To quantify this leakage, we introduce complementary measured- and unmeasured-subspace k-space dispersion metrics (MSD/USD). We then present Measured-Subspace Consistency (MSC), a training-free terminal correction that wraps any compatible image-space posterior sampler with a standard multi-coil consistency lock. The ideal lock follows classical range/null-space data consistency. Our contribution is to repurpose it as a black-box posterior audit and correction rather than a new reconstructor or learned sampler. Theoretically, we prove that the ideal transform confines pairwise sample differences to the MRI null space and bound the residual cross-subspace coupling left by practical sensitivity-weighted implementations. Across six base samplers and two MRI anatomies, including out-of-distribution transfer where a knee prior reconstructs brain, MSC substantially reduces measured-subspace dispersion for Soft samplers (a median 16.5x reduction for DPS across five brain contrasts, up to ~29x), while preserving unmeasured-subspace diversity and acting as a near-identity map for Consistent ones. Furthermore, MSC maintains or modestly improves PSNR/SSIM, with no retraining, retuning, or significant computational overhead.

0

cs.CV 2026-06-29

License plate recognition reaches 11.5 FPS on embedded FPGA

by Anuki Pasqual, Dulan Lokugeegana +4 more

An Embedded Real-Time License Plate Recognition System for Complex Traffic Scenes

Lightweight quantized CNNs handle complex traffic scenes with diverse vehicles on Xilinx Kria KV260

abstract click to expand

Vehicle license plate recognition is an integral component of intelligent transportation systems. In this work, we present an embedded real-time license plate recognition system customized for developing countries. We address the challenge of handling complex, unstructured traffic scenes with diverse vehicle types while implementing the system on an embedded platform for low-cost deployment. Our method consists of license plate detection on a multi-vehicle image, followed by character recognition on the detected license plates. Both steps use lightweight convolutional neural networks to balance accuracy and efficiency. We also introduce the SL-LPR dataset of Sri Lankan road images, which contains a variety of vehicle types and traffic conditions typically seen in developing countries. On this dataset, the license plate detection and character recognition models achieved 93.6% mAP and 87.88% accuracy, respectively, and were competitive against larger models on several public datasets. To achieve real-time performance in a resource-constrained embedded environment, we applied low-bitwidth quantization using the Brevitas library and implemented FPGA acceleration for the models using the FINN framework. The end-to-end system can operate at 11.5~FPS when implemented on the Xilinx Kria KV260 platform. These results demonstrate that our system is effective for real-time license plate recognition on an embedded device, even in complex traffic scenarios. The SL-LPR dataset is available for research use at: https://github.com/sl-lpr-uom/SL-LPR.git.

0

eess.IV 2026-06-29

Zero-shot DIP restores microscopy images without training data

by Xiangyu Qian, Jing Liu +3 more

A Zero-Shot Deep Image Prior Framework for Denoising and Deconvolution in Fluorescence Microscopy

Sequential autoencoding and Richardson-Lucy guidance improve SNR and resolution on cellular structures in the BioSR dataset.

abstract click to expand

Fluorescence microscopy images are degraded by noise and diffraction-induced blur, which compromise structural fidelity and limit quantitative analysis. Supervised deep learning methods achieve impressive restoration performance but require large-scale paired datasets that are difficult to obtain in practice. To address this issue, we propose SDIP, a zero-shot deep image prior (DIP) framework that sequentially performs denoising and deconvolution without external training data. An aSeqDIP-based module first suppresses noise while preserving fine structures through sequential autoencoding regularization. In the deconvolution stage, a wavelet-based background correction step is incorporated before the proposed RLG-DIP module performs artifact-reduced deconvolution. RLG-DIP uses the Richardson-Lucy deconvolution result as a physically consistent guidance prior, integrating the imaging model with the implicit prior of DIP to stabilize the ill-posed deconvolution process. Experiments on the BioSR dataset across multiple cellular structures demonstrate that SDIP improves both signal-to-noise ratio and resolution, achieving superior visual quality and improved quantitative performance on most evaluated structures. The proposed framework may also provide useful insights for designing physically guided DIP methods for other inverse problems.

0

physics.optics 2026-06-29

Photonic crystal patterns fingerprint silicon photonic chips

by Liton Kumar Biswas, M Shafkat M Khan +4 more

Enhancing Co-packaging Optics Enabled Silicon Photonics Security Assurance Hardware Fingerprinting

Embedded nanostructures produce unique narrowband peaks using only standard lithography and no added steps.

abstract click to expand

Silicon photonics enables integration of optical components using standard semiconductor processes, greatly improving data communication bandwidth and energy efficiency. However, photonics integrated circuits (PICs) face unique security challenges, such as counterfeit or tampering threats, that conventional electronic security methods do not address. We propose a novel hardware fingerprinting technique that embeds two dimensional photonic crystal patterns into the density control filler regions of a PIC. Each PhC pattern is designed to resonate a specific visible to near infrared wavelengths, producing a distinctive optical signature (based on wavelength, polarization, and incident angle) for each device. Finite difference time domain (FDTD) simulation using ANSYS Lumerical is employed to optimize nanostructure dimensions and spacing so that each device's reflection/absorption spectrum contains unique narrowband peaks. No extra fabrication steps or materials are required beyond standard lithography, keeping costs low. The embedded nanostructures have sub-50nm precision, making forgery extremely difficult. Our method yields a high resolution, scalable fingerprint for silicon photonic chips, enabling cost-effective device authentication and improved supply chain security.

0

cs.CV 2026-06-26

Decoupling predicates by transformation behavior under yaw shifts produces…

by Jingjun Sun, Chaowei Wang +5 more

Not All Relations Rotate Alike: Transformation-Aware Decoupling for Viewpoint-Robust 3D Scene Graph Generation

Separate stable and directional branches improve relation predictions under viewpoint change without rotation training data.

abstract click to expand

3D Scene Graph Generation (3DSGG) represents 3D scenes as structured object-relation-object graphs, providing a compact relational abstraction for spatial understanding. In embodied intelligence settings, the same 3D scene may be observed by agents from viewpoints that differ by yaw rotations. However, current 3DSGG models often fail to produce relation predictions that follow the expected transformation behavior under such viewpoint shifts. This behavior reveals an empirical mismatch related to predicate-level transformation heterogeneity: directional predicates such as left, front, right, and behind should transform with the observation frame, whereas most contact, support, and semantic predicates such as standing on and attached to should remain stable. To reduce this mismatch, we propose Transformation-Aware Decoupling (TAD), a viewpoint-robust 3DSGG framework that decouples relation reasoning according to predicate transformation behavior and is supported by viewpoint-stable object representations. TAD decomposes relation reasoning into two parts: one learns cues that should stay stable across viewpoints, while the other learns directional cues that should change with the observation frame. The two parts are merged for standard multi-label predicate prediction. Transformation-specific descriptors and group-aware auxiliary supervision encourage the two branches to capture complementary relation cues. Extensive experiments on 3DSSG show that TAD achieves state-of-the-art robustness under yaw viewpoint changes without training-time rotation augmentation, while maintaining competitive performance under the standard benchmark. The project page is available at https://tad-predicate.github.io/.

0

cs.CV 2026-06-26

Pseudo-text 3D detector reaches 0.58 mAP on organ localization in CT

by Siqi Chen, Han Gong +4 more

Pseudo-Text-Conditioned 3D Grounding DINO for Organ Localization in Abdominal CT

Frozen class tokens let a Grounding-DINO variant localize liver, spleen and kidneys on 193 volumes without real text input.

abstract click to expand

Reliable organ localization in abdominal CT can provide spatial priors for downstream trauma analysis. We propose CT-3GDINO, a lightweight 3D detector that adapts a Grounding-DINO-style query-based architecture to fixed organ localization using frozen pseudo-text class tokens instead of a real text encoder. The model combines a Swin3D visual backbone, bidirectional feature enhancement, pseudo-text-guided query selection, and a cross-modality decoder to predict normalized 3D boxes for liver, spleen, left kidney, right kidney, and bowel. We train and evaluate on 193 matched RSNA/RATIC CT volumes with segmentation-derived boxes. The best multi-scale model, trained from scratch, achieves 0.5830 overall top-1 class-wise mAP over 3D IoU thresholds from 0.1 to 0.7, outperforming fixed- and trainable-backbone classification-pretrained variants with 0.5570 and 0.4657 mAP. Performance is strong for coarse localization, with 0.9649 AP at IoU 0.1, but remains limited for strict box alignment, with 0.1552 AP at IoU 0.7. These results establish CT-3GDINO as an open-source baseline for pseudo-text-conditioned 3D organ localization and motivate future work on localization-aware pretraining, richer multimodal conditioning, and injury-focused detection.

0

eess.IV 2026-06-26

Noise2Inverse trains CT reconstructor without ground truth

by Antti Sällinen, Siiri Rautio +2 more

Enabling self-supervised learned primal dual with Noise2Inverse

Splitting angular measurements with independent noise lets the primal-dual network learn iterative reconstruction from noisy data alone.

abstract click to expand

X-ray computed tomography reconstruction is an ill-posed inverse problem, particularly in low-dose and sparse-angle settings where measurements are noisy and incomplete. While learned reconstruction methods such as the Learned Primal-Dual algorithm achieve strong performance, they typically rely on supervised training with access to ground-truth data, which is often unavailable in practice. In this work, we propose a self-supervised reconstruction method by extending the Noise2Inverse framework to the Learned Primal-Dual algorithm. The resulting approach, called Noise2Inverse Learned Primal-Dual (N2I-LPD), enables training of a learned iterative reconstruction operator without ground-truth images by exploiting the statistical independence of noise in distinct measurements with respect to angular rotation of the CT-scan. We compare the proposed method with classical reconstruction methods, as well as neural network-based approaches such as a U-Net trained within the same N2I framework. The results demonstrate that N2I-LPD achieves improved reconstruction quality, highlighting the potential of combining learned reconstruction operators with self-supervised training strategies for practical CT imaging scenarios where ground-truth data is unavailable.

0

quant-ph 2026-06-26

Quantum autoencoder flags MRI anomalies by compression resistance

by Santanu Ganguly, Xing Liang +1 more

Compression-Driven Anomaly Detection in Brain MRI Using an Interpretable Quantum Autoencoder

Trash-qubit scores on brain patches reach 0.95 slice-level AUC and localize to tumors better than classical baselines.

abstract click to expand

We study a quantum autoencoder (QAE) for compression-driven anomaly detection in brain MRI data. The approach leverages angle encoding to map image patches into quantum states, followed by a variational encoder-decoder architecture trained to discard information via auxiliary trash qubits. Anomaly scores reflect the degree to which inputs resist compression relative to normal data, with higher scores corresponding to deviations from the learned normal manifold. Evaluated on publicly available brain MRI DICOM datasets, the method achieves a slice-level ROC-AUC of approximately 0.95 and a patch-level ROC-AUC of approximately 0.813, outperforming classical autoencoder and PCA baselines. Analysis of the learned parameters reveals a pronounced encoder-decoder asymmetry, where effective anomaly detection arises from structured information compression within the encoder rather than increased parameter magnitude or decoder expressivity. This results in a controlled compression-reconstruction trade-off with a clear operating regime that supports principled threshold selection. Qualitative evaluation further shows that the QAE produces spatially localized anomaly heatmaps aligned with tumorous regions. The results, supported by promising baseline performances, demonstrate that quantum autoencoders provide an interpretable and controllable mechanism for anomaly detection based on incompressibility with respect to a learned latent representation. This work highlights the potential of quantum autoencoders as a principled tool for studying compression dynamics in quantum machine learning, with promising implications for decision support in medical imaging workflows.

0

eess.IV 2026-06-26

Text-guided loss steers vision encoder for satellite change captions

by Yelin Wang, Zijia Song +5 more

DFM: Difference Feature Modeling with Text-Guided Gated Contrastive Loss for Remote Sensing Image Change Captioning

The method reframes training so the model focuses on meaningful differences between image pairs instead of easy vocabulary.

abstract click to expand

The primary goal of Remote Sensing Image Change Captioning (RSICC) is to automatically generate descriptions of changes between remote sensing images captured at different time points. Existing models still rely on a single autoregressive generation paradigm, which tends to prioritize learning easily generated vocabulary over capturing discriminative differences between images. To address this, we reframe the training paradigm and propose a novel Difference Feature Modeling (DFM) framework. Specifically, we introduce a Text-guided Gated Contrastive Loss (TGCL) to guide the vision encoder to extract critical features from a text-modal perspective. Additionally, we incorporate a pre-trained Change Detection model to transfer stable change detection knowledge. In order to further enhance the representation, we design a Joint Feature Modeling (JFM) module to achieve the fusion of multi-scale difference representations, thereby capturing comprehensive spatiotemporal variations between multi-temporal images. Extensive experiments on multiple datasets demonstrate the effectiveness of our approach.

0

cs.CV 2026-06-26

Event-based system estimates ball spin at 750 Hz with 3 ms latency

by Yunpu Hu, Fabian Schilling +7 more

Event-based Gaze Control System for Accurate Real-time Spin Estimation in Professional Ball Games

Hybrid tracking and sphere-based contrast maximization deliver accurate real-time spin data in professional table tennis.

abstract click to expand

Spin plays a crucial role in many ball sports due to its effect on the trajectory of the ball. Vision-based estimation of the ball's spin during a game with conventional cameras is challenging due to the ball's small size, high speed, and fast rotation. To address these challenges, we propose an event-based active vision system that can track unmodified balls and measure their spin in real time. The system consists of an event camera for its high temporal resolution and minimal motion blur, high-speed pan/tilt galvanometer mirrors to keep the ball in the field of view, and a low-latency focus-tunable telephoto lens to increase the spatial resolution on the ball and keep it in focus. To track the ball, we use a hybrid approach that combines 2D event-based detection for centering and 3D positions from a ball localization system for re-initialization. For high-accuracy spin estimation, we propose an offline method that performs contrast maximization on the sphere (s-CMax). This method achieves state-of-the-art accuracy on static balls across multiple sports (table tennis, baseball, tennis, and golf), with mean magnitude and axis errors of 1.2% and 1.5 degrees, respectively. We then develop a low-latency online method for table tennis as a case study in real-time applications. This method uses an uncertainty-aware convolutional neural network trained on pseudo-ground-truth spin labels from the offline approach, combined with a GPU-accelerated batch implementation of contrast maximization for refinement. We demonstrate reliable tracking and spin estimation with a three-view setup during professional table tennis matches, with high accuracy (8.8% magnitude and 6.4 degrees axis mismatch w.r.t. the offline method), 3 ms latency, and 750 Hz throughput.

0

eess.IV 2026-06-26

Null-space priors keep medical slice reconstructions exactly consistent with observations

by Haofei Song, Siyuan Xu +4 more

Dual-Prior Guided Null-Space Learning with Mixture-of-Splines for Arbitrary Medical Slice Super-Resolution

Method projects outputs onto acquired slices with zero error and mixes B-splines for region-specific continuity at arbitrary scales

abstract click to expand

Arbitrary slice super-resolution reconstructs isotropic volumes from anisotropic clinical acquisitions by synthesizing intermediate slices at arbitrary scales. However, treating this ill-posed inverse problem as unconstrained residual-based regression risks hallucinating anatomically implausible structures or altering the originally observed data. To address both concerns, this paper presents the Dual-Prior Null-space Learning (DP-NSL) framework, which reformulates the task as a constrained recovery process guided by two complementary priors. A Measurement-Consistent Projection (MCP) enforces a Deterministic Observation Prior: the reconstruction undergoes an exact orthogonal projection that reproduces every acquired slice with zero error, confining all learned details to the unobservable null space. Within this null space, a Mixture-of-Splines (MoS) module imposes a Geometric Continuity Prior by dynamically mixing B-spline experts of different analytic orders, allowing each anatomical region to be modeled with a content-aware level of continuity. To promote spatial coherence, a Local Spatial Consistency Decoder (LSCD) further injects local inductive bias. Experiments on three CT and one MRI benchmark show that DP-NSL outperforms existing approaches while strictly preserving measurement consistency. Code is available at https://github.com/DeepMed-Lab-ECNU/Medical-Image-Reconstruction.

0

eess.IV 2026-06-26

Diffusion model with multi-level fusion improves skin lesion segmentation

by Jingjun Gu, Chaojie Shen +4 more

MLFFM-SegDiff: A Multi-Level Feature Fusion Diffusion Model for Skin Lesion Segmentation

Dual-path encoder and MLFFM raise Jaccard to 0.8546 and Dice to 0.9207 on ISIC2018, PH2, HAM10000.

abstract click to expand

Skin lesion segmentation is a key task in computer-aided dermatological diagnosis, where accuracy directly impacts downstream analysis and disease classification. However, dermoscopic images are challenging due to blurred boundaries, low contrast, large shape variations, and artifacts such as hair and shadows. Recently, diffusion models have shown strong performance in medical image segmentation thanks to their progressive denoising and distribution modeling capabilities. Nevertheless, existing diffusion-based methods still suffer from limited cross-level feature interaction and insufficient boundary detail recovery. To address these issues, we propose MLFFM-SegDiff, a multi-level feature fusion diffusion model for skin lesion segmentation. Built on a diffusion framework, the method introduces a dual-path U-Net encoder, a Multi-Level Feature Fusion Module (MLFFM), and a boundary-sensitive loss function. The dual-path encoder enhances interaction between noisy mask features and dermoscopic image features. MLFFM improves skip connections via attention, scale alignment, and adaptive cross-level fusion. These designs enable the decoder to jointly leverage shallow boundary cues and deep semantic representations, improving mask reconstruction quality. Experiments on ISIC2018, PH2, and HAM10000 demonstrate that MLFFM-SegDiff outperforms representative methods including DermoSegDiff, U-Net, and SwinUNETR across Accuracy, F1-score, Jaccard index, Recall, and Dice. In particular, it achieves an average Jaccard index of 0.8546 and Dice coefficient of 0.9207. These results validate the effectiveness of the proposed multi-level feature fusion strategy for improving lesion segmentation performance. The code will be released at https://github.com/Qacket/MLFFM-SegDiff.git after publication.

0

cs.CV 2026-06-26

Fractional relaxation sharpens event timing in simulation

by Langyi Chen, Chuanzhi Xu +7 more

FracEvent: Event-Camera Simulation via Fractional-Relaxation Pixel Dynamics

Retained memory modes produce event streams that transfer better to reconstruction and flow tasks than contrast-threshold baselines.

abstract click to expand

Event cameras asynchronously report brightness changes with microsecond-level temporal resolution, but real event data remain difficult to collect at scale because specialized sensors, careful synchronization, and task-specific annotations are required. Event-camera simulation is therefore important to event-based vision tasks. Most practical simulators build on contrast-threshold event generation, some with additional filtering, stochastic noise, or hand-tuned sensor parameters. While effective, such formulations often simplify the temporal structure produced by the lifecycle of each pixel, which can distort event timing and weaken downstream transfer. We introduce FracEvent, an event simulator that models this pixel-level lifecycle with fractional-relaxation voltage dynamics. Given a log-intensity trajectory, FracEvent drives a compact stack of relaxation modes, combines their responses into a voltage state, emits ON/OFF events by localizing threshold crossings on the continuous voltage trajectory, and updates the reference while retaining the underlying memory modes. This retained state links residual voltage response to later event timing. We evaluate FracEvent through event-stream comparison and downstream transfer on image reconstruction and optical flow estimation. Across multiple datasets, FracEvent improves the temporal structure of generated events and achieves stronger downstream-transfer results than competing simulator baselines, showing its practical value for event-camera simulation.

0

cs.CV 2026-06-26

Selective token refinement boosts task performance

by Hongjae Lee, Sojung Kang +2 more

TaskTok: Delving into Task Tokens for Task-driven Image Restoration

A learnable switch picks relevant latent tokens for light refinement, raising accuracy in classification, segmentation and detection while l

abstract click to expand

While traditional image restoration focuses on perceptual quality, Task-Driven Image Restoration (TDIR) aims to maximize the performance of downstream high-level vision tasks. Recent approaches leveraging generative priors have shown promise for TDIR; however, they typically suffer from computational inefficiency and potential semantic alteration by indiscriminately updating all latent tokens. In this paper, we posit that not all visual information is equally important for machine perception. Through an analysis of the latent token space, we observe that task-relevant cues are unevenly distributed across the token sequence, exhibiting index-wise specialization. This suggests that selectively refining a subset of tokens can be sufficient for task-driven objectives. Leveraging this insight, we propose TaskTok, a novel framework that selectively restores only task-relevant tokens via a learnable token switch and a lightweight token refinement module. Extensive experiments across image classification, semantic segmentation, and object detection demonstrate that TaskTok significantly enhances task performance with high computational efficiency. The source code is available at https://github.com/jimmy9704/TaskTok

0

eess.IV 2026-06-26

ResNet18 detects brain tumors at 97% accuracy in MRI scans

by Annapurna V K, Asha N +3 more

Automated brain tumor detection in MRI images using CNN and ResNet architectures

Shallower network beats deeper ResNet50 on 3929-image dataset, pointing to better generalization for limited medical data.

abstract click to expand

Deep learning has shown significant potential in medical image analysis, particularly for disease detection using MRI scans. Accurate and early diagnosis of brain tumors remains challenging due to the complexity of brain structures and reliance on manual interpretation. This work presents an automated deep learning-based approach for brain tumor detection from MRI images using Convolutional Neural Networks and Residual Networks. Transfer learning is applied with two pretrained architectures, ResNet18 and ResNet50, to classify MRI scans into tumor and non-tumor categories. Experiments are conducted on a dataset of 3,929 brain MRI images, evaluating the impact of model depth and fine-tuning strategies. The results show that ResNet18 achieves a higher accuracy of 97% compared to 96% for ResNet50, demonstrating better generalization on limited medical data. The proposed framework enables fast, accurate, and cost-effective brain tumor detection, supporting early diagnosis and clinical decision-making.

0

eess.IV 2026-06-25

Clustering reveals mammographic phenotypes linked to cancer risk

by Ruiyu Jia, Yanqi Xu +3 more

Revealing Mammographic Phenotypes in Deep Learning Breast Cancer Risk Models

Patch embeddings from a pre-trained model surface recurring patterns tied to 5-year risk, including dense tissue, calcifications, and artifa

abstract click to expand

Mammogram-based deep learning models have improved breast cancer risk prediction, but the learned imaging patterns remain underexplored. Existing interpretability methods rely on single-image saliency maps, failing to identify recurring mammographic phenotypes across large patient cohorts. By clustering patch embeddings from a pre-trained model, Mirai, we isolate recurring phenotypes linked to 5-year cancer risk. Analyses show risk-increasing phenotypes capture complex structures (e.g., dense tissue, microcalcifications) and shortcut artifacts (e.g., clips). These phenotypes correlate strongly with older age and higher BI-RADS density. Our framework connects tissue patterns to AI risk scores, revealing clinical signatures and potential latent model confounders.

0

eess.IV 2026-06-25

AI experiments produce X-ray design rules for CoWoS packages

by Katayoon Yahyaei, M Shafkat M Khan +3 more

Design Guidelines for In-line X-ray Inspection in Advanced Packaging Technology: A CoWoS Case Study

Framework analyzes parameters and materials to raise inspection image quality and defect detection in advanced semiconductor packaging.

abstract click to expand

The shift towards advanced packaging technologies, including 2.5D and 3D integration, addresses the limitations of traditional methods while meeting increasing demands for performance, miniaturization, and efficiency. These methods enhance functionality and support heterogeneous integration but also introduce metrology challenges due to complex, three-dimensional structures. X-ray imaging, crucial for nondestructive inspection, faces compatibility issues such as material density similarities and noise scattering. To address these challenges, we propose a framework based on AI-integrated Design of Experiment (DoE) to develop design guidelines to optimize X-ray compatibility during the design stage. This framework, demonstrated through a case study on Chip-on-Wafer-on-Substrate (CoWoS) packaging, systematically analyzes design parameters and material properties to develop guidelines for improved inspection accuracy. Our method integrates AI to predict outcomes and optimize processes, ensuring high-quality X-ray images and enhancing defect detection. Implementing these guidelines can significantly improve inspection accuracy and reliability, reducing production costs and supporting the efficiency and scalability of advanced semiconductor technologies.

0

cs.AR 2026-06-25

NEMS mechanisms add physical security to chip packaging

by Himanandhan Reddy Kottur, Pavanbabu Arjunamahanthi +4 more

Nanoelectromechanical Systems (NEMS) for Hardware Security in Advanced Packaging

They use mechanical variability for tamper detection and low-power authentication where digital methods are vulnerable.

abstract click to expand

As hardware security threats escalate across semiconductor manufacturing and advanced packaging, there is a growing need for novel physical mechanisms to counter sophisticated attacks such as tampering, counterfeiting, and supply chain infiltration. This paper presents Nanoelectromechanical Systems (NEMS) as an emerging class of hardware security primitives that enable physical assurance, tamper detection, and authentication at the device level. Leveraging mechanisms such as NEMS-based Physically Unclonable Functions (PUFs), shape memory materials, resonance-based fingerprints, and physical unlocking architectures, these systems offer enhanced resilience to reverse engineering, side-channel attacks, and environmental degradation. By harnessing mechanical unpredictability and fabrication-induced nanoscale variability, NEMS technologies introduce a physically robust and low-power alternative to conventional digital security methods. Their seamless integration into standard semiconductor workflows paves the way for scalable, verifiable, and secure solutions across defense, aerospace, critical infrastructure, and consumer electronics.

0

eess.IV 2026-06-25

Standard ABR boosts throughput for time-shifted MoQ clients

by Abanisenioluwa Orojo, Tanvir Redoy +2 more

An Evaluation of ABR Switching for Time-Shifted Clients in MoQ

Unmodified algorithms work for shifted playback and raise performance after rebuffering in simulations.

abstract click to expand

Media over QUIC enables ultra low latency video streaming over QUIC, but its default quality-switching semantics risk introducing playback gaps during periods of network congestion. The in-progress SWITCH specification for MOQ Transport aims to streamline rate adaptation for MoQ. In this work, we characterize the performance of SWITCH-style Adaptive Bitrate (ABR) for both live and time-shifted clients in a Mininet simulated topology. We validate that standard ABR algorithms can be directly applied to time-shifted playback without modification, yielding substantially higher throughput. We demonstrate that a subscriber can experience increased overall throughput after a rebuffering scenario, and we identify focal points for further optimizations of MoQ ABR switching.

0

eess.IV 2026-06-25

Gaussian Splatting Improves Stenosis Grading from Sparse MRIs

by Robin Y. Park, Mark C. Eid +5 more

Rendering Novel Views of MRI Using 3D Gaussian Splatting

Resampling spine scans into aligned planes beats raw images and voxel methods in grading accuracy experiments.

abstract click to expand

The objective of this paper is to improve radiological gradings measured on MRIs of spines, by resampling scans so that the new view planes are better aligned with the target anatomy than the original sparse images. To this end, we adapt 3D Gaussian Splatting to form a volumetric reconstruction starting from sparse anisotropic MRIs, and imaging planes aligned with the anatomy relevant for clinical evaluation are then sampled and rendered. The novel view plane is optimal for diagnostic radiological grading of the target anatomy, whereas the original MRI is not. The resampled scans are then used to predict ordinal severity grades of localised stenosis conditions in spinal MRIs. We compare our method against Voxel Interpolation resampling, which takes the average of inverse-distance weighted nearest neighbour intensities for each target coordinate. Experiments show that across all stenosis conditions, resampled scans using Gaussian Splatting produce more accurate stenosis gradings compared to the raw scans which do not include the complete anatomy in-plane, as well as images resampled using Voxel Interpolation.

0

cs.CV 2026-06-25

Vascular graphs add nothing to PE risk stratification

by Nathan Painchaud, Tristan Habémont +7 more

Pulmonary Embolism Risk Stratification from CTPA and Medical Records: Vascular Graphs Are Not All You Need

Medical records and cardiac biomarkers suffice; GNNs on vascular trees match but do not beat tabular baselines on global features.

abstract click to expand

Risk stratification for pulmonary embolism (PE) is critical for clinical decision-making. Stratification guidelines are based on patient medical records, parameters measured from computed tomography pulmonary angiography (CTPA), and blood tests. However, blood tests are often missing in routine practice. This work studies whether state-of-the-art models can accurately classify risk stratification from only medical records and biomarkers extracted from CTPA images. We benchmark different approaches to combine medical records and cardiac biomarkers with rich pulmonary vascular information; we add vascular biomarkers to tabular models and apply graph neural networks (GNNs) on the vascular tree's intrinsic graph representation. We use a private dataset (n=353) with uniquely complete data for PE risk stratification. Our results show that, among global features, medical records and cardiac biomarkers are the most significant predictors, while vascular biomarkers do not further improve stratification. Even more surprising, even GNNs on vascular graphs fail to outperform strong tabular baseline on global features. We consider hypotheses, on both models and data, that could explain this suboptimal performance. Our investigation suggests that, counter-intuitively, vascular graphs might hold no discriminative information for PE risk stratification. Code is available from https://github.com/creatis-myriad/GENESIS.

0

eess.IV 2026-06-25

Diffusion prior cuts noise in RL microscopy deconvolution

by Hao Chen, Scott S. Howard

Improving Richardson--Lucy Deconvolution with Diffusion Priors for Fluorescence Microscopy

Score-based guidance inside iterations preserves fine structures at low photon counts without TV-style oversmoothing.

abstract click to expand

Richardson--Lucy (RL) deconvolution improves fluorescence microscopy images by recovering details lost to diffraction. It estimates the original fluorescence signal that most likely produced the measured photon counts under a Poisson imaging model. Although RL incorporates a physical model of fluorescence image formation and can improve contrast, deconvolution remains fundamentally ill-posed, and the measurements alone provide limited evidence for reliably reconstructing fine biological structure. Without additional structural guidance, RL can amplify noise and exhibit unstable convergence in low-photon regimes. Regularizers such as total variation (TV) reduce this instability but often introduce oversmoothing. Here, we investigate learned generative priors as a form of structural guidance for RL by integrating a score-based diffusion prior into a decoupled inverse-problem framework for fluorescence microscopy deconvolution. The diffusion prior is used during the RL optimization iterations, while RL retains Poisson data consistency. We validate the framework across diverse biological samples and cellular morphologies. The results show reduced RL noise amplification with improved preservation of weak filamentous and punctate structures under low photon counts.

0

cs.CV 2026-06-25

Self-supervised model estimates urban tree biomass at R²=0.57

by Jose Bermudez (1), Zilong Zhong (1) +15 more

Self-Supervised Tree-level Biomass Estimation in Urban Environments From Airborne LiDAR and Optical Observations

Crown-level maps from standard LiDAR and photos cover 90,000 trees across 810 km² and show 39 Gg C net gain over five years.

abstract click to expand

Urban tree biomass remains less spatially explicitly quantified than biomass in managed forests because many estimates rely on inventories or coarse products that cannot resolve individual crowns or fine-scale heterogeneity. We present a crown-level above-ground biomass (AGB) framework for an 810~km$^2$ landscape in Ontario, Canada, using leaf-off airborne LiDAR (8--10~pulses~m$^{-2}$) and near-infrared RGB orthophotography (0.16--0.20~m) from 2018 and 2023. A dual-stream cross-attention network trained on rule-based pseudo-labels produced semantic marks for buildings, needleleaf trees, and deciduous trees, supporting crown delineation and functional-type assignment. On independently annotated withheld tiles, global/mean precision, recall, and Dice scores were 0.86, 0.83, and 0.84. Crowns were delineated with multiscale watershed segmentation in mapped tree areas, and AGB was estimated from a crown area--height power-law proxy calibrated to species-specific allometry (Lambert et al., 2005) for 21,921 inventory trees. For 18,713 inventory--segment matched pairs from a 90,726-tree held-out test set, AGB prediction achieved $R^2=0.609$ using inventory crown geometry and $R^2=0.570$ under operational segmentation, identifying crown delineation as the remaining uncertainty source. Aggregated to 30~m, estimates yielded total AGB stocks of 1.73~Tg in 2018 and 1.81~Tg in 2023 (811--850~Gg~C), local densities up to ${\sim}140$~Mg~ha$^{-1}$ along the Niagara Escarpment, and a net carbon gain of 39~Gg~C over five years. Deep-ensemble uncertainty maps highlighted high-epistemic-uncertainty areas linked to underrepresented land covers and guided assignment of uncertain crowns to a pooled allometric equation. The framework uses standard provincial data, requires no manual annotation, and produces a public bitemporal crown-level AGB database for trees outside forests at management-relevant resolution.

0

cs.RO 2026-06-25

Event cameras cut table tennis bounce error by 36% for robots

by Raphaela Kreiser, Asude Aydin +4 more

1000 Rallies: An Event-Camera Dataset and Real-Time Learned Ball-State Estimation for Robotic Table Tennis

A dataset of 1000 rallies trains a CNN to estimate ball velocity from events and feeds it to a Kalman filter for real-time robotic rallies.

abstract click to expand

Robotic table tennis has emerged as a compelling benchmark for real-time robotic perception due to its fast ball dynamics and stringent timing requirements. Accurate, high-frequency, and low-latency ball state estimation is critical for reliable trajectory prediction and timely control. Traditional frame-based cameras face an inherent trade-off: low frame rates leave temporal blind spots that miss fast-moving objects and high frame rates raise data and computational cost. Event cameras instead offer microsecond temporal resolution and, under sufficient illumination, remain largely free of motion blur even at high ball speeds. However, the community lacks large-scale datasets to develop and benchmark event-based perception in realistic sports scenarios. We address this gap by introducing the first large-scale event-camera dataset for table tennis, comprising over 1000 rallies from a diverse group of players ranging from amateurs to elite-level athletes. Each recording captures the event stream alongside 14 synchronized high-speed frame-based cameras at 200 FPS, which we use to produce 1 kHz pseudo ground-truth labels for ball position, velocity, and spin. Building on this dataset, we train a convolutional neural network robust to background player motion that jointly estimates the ball's position and velocity in the image-plane from events. Treating the predicted velocity as an additional measurement in the Kalman filter reduces bounce-point prediction error by 36% relative to a position-only baseline. Finally, we close the perception-action loop by integrating the event-based system with a St\"aubli robotic arm, enabling the first real-time human-robot table tennis rallies driven by event-based perception.

0

eess.IV 2026-06-25

Cross-attention model predicts imatinib response in GIST

by Fariba Tohidinezhad, Douwe J. Spaanderman +15 more

Cross-Attention Multimodal Learning for Predicting Response to Neoadjuvant Imatinib in Gastrointestinal Stromal Tumors: A Multicenter Retrospective Study

CT scans plus clinical data reach internal AUC 0.99 but drop to 0.60-0.63 on external centers, with attention maps showing key differing fea

abstract click to expand

Background: Response to neoadjuvant imatinib in gastrointestinal stromal tumors (GISTs) is highly variable and cannot be reliably predicted using current clinical or molecular markers. This study developed and evaluated an explainable multimodal deep learning framework integrating computed tomography (CT) imaging and clinical variables to predict treatment response. Methods: Patients from four tertiary centers were retrospectively included between 2000-2023 in independent pretraining (n=935) and prediction (n=213) cohorts. A cross-attention framework integrating clinical variables and tumor-centered CT imaging was developed to predict response to neoadjuvant imatinib. Two training strategies were evaluated: (1) self-supervised pretraining with low-rank adaptation and (2) training from scratch. Hyperparameters were optimized using SMAC3. Performance was assessed through internal cross-validation and external testing. Ablation analyses and attention-based explanations were used to quantify modality contributions. Results: Among 213 patients (54.5% responders), responders had larger tumors (112 vs. 89 mm, P=0.026), higher mitotic index (3 vs. 0, P<0.001), and more frequent KIT mutations (69.0% vs. 56.7%, P=0.019). Cross-attention models achieved the highest internal performance (AUC up to 0.99) but lower external performance (AUC 0.60-0.63). Clinical-only performance was moderate (AUC 0.66), whereas imaging-only models showed limited generalizability (AUC 0.56-0.66). Explainability analyses identified significant differences in feature importance between responders and non-responders, including CD117, BRAF, PDGFRA, age, sex, disease status, and comorbidities (FDR-adjusted P<=0.036). Conclusion: The cross-attention framework shows potential for improving imatinib response prediction in GIST while providing interpretable insights into multimodal determinants of treatment response.

0

cs.CV 2026-06-25

Semantic selection transmits images at 0.074 bpp with 44.6% bits

by Chenyang Zhang, Changwang Liu +5 more

Semantic-Aware Generative Image Transmission for Resource-Constrained Visual IoT Systems

Method hits 29.9 dB PSNR on Kodak and VisDrone scenes while using under half the bits of DeepJSCC reference.

abstract click to expand

Resource-constrained visual Internet of Things (IoT) systems, such as edge cameras, unmanned sensing platforms, industrial inspection nodes, and remote monitoring sensors, often need to transmit task-relevant visual evidence over low-rate wireless links to an edge/cloud service. Existing image communication methods usually compress or transmit complete global representations, leaving limited room to exploit receiver-side generative restoration. This paper proposes a semantic-aware generative image transmission framework for edge-assisted visual IoT. The image captured by an IoT visual sensor is encoded into a discrete token grid by a VQ encoder. At the IoT transmitter or nearby gateway, token recoverability, estimated from prediction entropy and local structure complexity, is fused with semantic importance obtained from instance segmentation and category-aware scoring. A spatial dispersal sampler then selects the tokens to be transmitted under a bitrate budget. The transmitter sends only the quantization indices of kept tokens and a binary mask map, while the edge/cloud receiver recovers masked tokens through MaskGIT with Halton sequence scheduling. Experiments on Kodak and VisDrone scenes under AWGN and Rayleigh channels show that the proposed method provides a flexible bitrate-quality tradeoff for narrowband visual IoT links. At 0.074 bpp, it uses 44.6% of the transmitted bits of the 0.167-bpp DeepJSCC/WITT reference while achieving 29.9 dB PSNR. A pseudo-GT downstream detection study on Kodak further shows that semantic-aware masking preserves task-relevant objects better than random masking at both 30% and 50% mask ratios.

0

eess.IV 2026-06-25

One network segments blastocyst parts and predicts implantation at 80% F1

by Zahra Asghari Varzaneh, Reza Khoshkangini +3 more

Blasto-Net: An Explainable Multi-Task Learning for Blastocyst Segmentation, Grading, and Implantation Prediction

Blasto-Net runs segmentation, grading and outcome prediction together on the HMC dataset with Dice scores above 88 percent.

abstract click to expand

This study introduces Blasto-Net, a multi-task deep learning model for comprehensive blastocyst analysis. The proposed model performs three tasks simultaneously in a single forward pass: segmentation of the ZP, TE, and ICM compartments, morphological grading, and implantation outcome prediction. Accurate blastocyst analysis in in vitro fertilization (IVF) is challenging. The compartments often have similar textures but very different structures. To address these challenges, Blasto-Net employs an EfficientNet-B3 encoder with a UNet-style decoder enhanced by the Convolutional Block Attention Module (CBAM) and a novel Edge-Aware Attention Module (EAAM) to effectively capture both semantic and boundary information. To handle distinct compartment topologies, the network employs specialized segmentation heads and a composite region- and boundary-based loss. Additionally, Grad-CAM++ visualizations are used to verify the anatomical consistency of the model's predictions. Evaluated on a public HMC blastocyst dataset, Blasto-Net achieves Dice scores of 94.93%, 91.60%, and 88.82% for ICM, ZP, and TE, respectively, alongside an implantation F1-score of 80.0%. These results demonstrate that Blasto-Net offers an accurate, interpretable, and efficient solution for automated blastocyst assessment, with strong potential to support clinical decision-making in IVF.

0

eess.IV 2026-06-25

DACL lifts fetal US Dice 2.77% at 5% labels

by Fangyijie Wang, Guénolé Silvestre +2 more

Dual Agreement Consistency Learning for Semi-Supervised Fetal Ultrasound Segmentation

By aligning both probability distributions and entropy-based confidence between a CNN and a Transformer on unlabeled scans

abstract click to expand

Maternal-fetal US is the primary imaging modality for monitoring fetal development, yet accurate automated segmentation remains challenging due to the scarcity of pixel-level annotations. To address this issue, we propose DACL, a semi-supervised framework for robust fetal US image segmentation. DACL jointly trains a deployment-oriented lightweight convolutional network (1.47\thinsp\mathrm{M} parameters) and a Transformer-based network, leveraging labeled data for supervised learning and unlabeled data via CPS. To enhance prediction stability, we introduce a dual-agreement consistency loss that couples pixel-wise probabilistic divergence with entropy-guided confidence alignment. Unlike conventional CPS methods that enforce agreement only at the prediction level, DACL explicitly regularizes both distributional alignment and uncertainty, thereby suppressing unreliable pseudo-labels and enabling stable cross-architecture pseudo-label learning under extreme annotation scarcity. Furthermore, an interpolation-based consistency strategy using mixup is applied to unlabeled samples to enhance robustness. Under 5% labeled data, DACL improves Dice by up to 2.77% and reduces HD95 by up to 14.69 mm compared with the strongest recent semi-supervised methods, demonstrating significant improvements in boundary accuracy on both fetal head and abdomen datasets. These results demonstrate the effectiveness of agreement-based consistency learning for annotation-efficient fetal US segmentation. Our code is on GitHub.

0

eess.IV 2026-06-24

Dimension expansion halves simulation cost for metalens design

by Shuo Huang, Mahsa Torfeh +4 more

Dimension expansion for simulation-efficient nanophotonic neural networks

DEN matches adjoint optimization while generalizing to thousands of targets using only differentiable simulations and no precomputed data.

abstract click to expand

Inverse design of nanophotonic structures is challenging due to the large design space, nonlinear structure-response relationships, and the high computational cost of iterative electromagnetic simulations. Existing deep-learning approaches typically rely on large precomputed datasets or libraries of optimized structures, which limits scalability to continuous and complex inverse-design tasks. We introduce a Dimension Expansion Network (DEN), a fully unsupervised, simulation-efficient framework for nanophotonic inverse design. DEN addresses the mismatch between low-dimensional design objectives and high-dimensional nanophotonic structures by transforming compact target parameters into structured, high-dimensional conditioning representations before inverse design. This improves target expressivity and conditioning quality for structure generation. The model is trained end-to-end using differentiable electromagnetic simulations, removing the need for any pre-generated dataset. We validate DEN on free-form metalens and asymmetric Y-splitter design problems. For metalens design, DEN achieves focal intensities comparable to adjoint-based optimization while reducing simulation cost by approximately 50% and generalizing across tens to thousands of focal targets within a shared focal region. For Y-splitter design, DEN accurately produces arbitrary power-splitting ratios using only 21 training targets and demonstrates robust broadband performance. Ablation studies and representation analyses show that dimension expansion enhances sensitivity to target variations, increases structural diversity, and reduces mode-collapse-like behavior. Overall, DEN provides a scalable conditioning strategy for inverse design with low-dimensional objectives, enabling efficient photonic design across large continuous target spaces.

0

cs.LG 2026-06-24

Energy minimization jointly retrieves three crop parameters from satellites

by Shubham Kumar Singh, Peilei Fan +3 more

An iterative energy-based multimodal transformer for joint retrieval of wheat soil moisture, leaf area index, and plant height from Sentinel-1 and Sentinel-2 time series

Iterative transformer on Sentinel-1 and Sentinel-2 time series reaches mean R^2 of 0.85 for soil moisture, leaf area index and plant height

abstract click to expand

Field-scale retrieval of surface soil moisture (SM), leaf area index (LAI), and plant height (PH) is essential for precision agriculture, yet it remains an ill-posed inverse problem. Concurrent variations in soil moisture and canopy density generate substantial ambiguities in radar backscatter and spectral responses, which reduces the effectiveness of traditional feedforward regression models in heterogeneous smallholder cropping systems. This study presents the Iterative Energy-Based Transformer (iEBT) for the joint retrieval of coupled soil-canopy states from Sentinel-1 C-band SAR and Sentinel-2 multispectral time series. Instead of direct regression, iEBT embeds multi-modal predictors within a shared sequence, produces an initial state estimate, and iteratively updates the target [SM, LAI, PH] vector through normalized gradient descent to minimize a learned scalar compatibility energy function. Using 700 quality-controlled field measurements from Varanasi, India, iEBT achieved the highest learned-model performance on the random test split, with a four-seed mean R^2 of 0.854 \pm 0.012 (R_SM^2 = 0.841, R_LAI^2 = 0.905, R_PH^2 = 0.821). WCM and PROSAIL were retained as physically interpretable SAR and optical reference models for comparison. Modality ablations confirmed that Sentinel-1 drives SM retrieval, while Sentinel-2 dominates LAI, whereas PH relies on combined structural-phenological signatures. Crucially, the model's terminal energy functions as an uncalibrated post-retrieval quality diagnostic; screening the 10% highest-energy samples markedly reduced target level root-mean-square errors. While leave-one-campaign-out validation highlights persistent cross-season domain shift challenges due to localized management variations, compatibility-guided multimodal fusion offers a structured self-diagnostic path toward reliable biophysical parameter estimation

0

eess.IV 2026-06-24

FID scores misalign with human judgment on Earth observation data

by Ümit Mert Çağlar, Alptekin Temizel

Benchmarking the Alignment of Data-Quality Metrics, Human Judgment and Land-Cover Segmentation Performance for Earth Observation

Synthetic images that score poorly on automatic metrics can still improve land-cover segmentation when mixed with real data.

abstract click to expand

Volume and quality of datasets are crucial for deep learning model training, yet they are often constrained by availability and data acquisition costs. Synthetic data augmentation can extend existing datasets with realistic images, and the quality of these images is generally assessed through fidelity metrics such as FID, KID, IS, LPIPS and SSIM that measure structural or distributional similarity. However, such metrics, including the widely used FID, focus on visual fidelity without reflecting downstream utility, and can diverge from human perception under perturbations that are imperceptible to human observers. In this work, we systematically evaluate Earth observation datasets alongside synthetic counterparts generated by deep generative models, comparing automatic metrics against human perception and downstream tasks. Our results reveal a stark misalignment: semantics-preserving perturbations such as rotation drastically alter metric scores while leaving human recognition unaffected, and synthetic samples that score poorly on automatic metrics achieve comparable or higher perceived realism, and can improve downstream performance when combined with real data. By benchmarking semantic segmentation models trained on mixed real-synthetic datasets, we demonstrate that quality metrics rooted in ImageNet-pretrained feature spaces are unreliable indicators for geospatial data. Our findings underscore that automatic quality evaluation of synthetic datasets should be grounded in downstream task performance and human evaluation.

0

cs.CV 2026-06-24

Diffusion model makes TEM images from just 15 samples

by Johannes Boehm, Bappaditya Dey

High-Fidelity Synthetic Transmission Electron Microscopy Image Generation Using Diffusion Probabilistic Models for Data-Limited Semiconductor Metrology

The approach allows training machine learning tools for semiconductor analysis without large real datasets.

abstract click to expand

Advanced semiconductor nodes drastically increased demand for Transmission Electron Microscopy (TEM), yet destructive sample preparation, slow imaging and high costs severely limit the availability of diverse datasets needed for downstream machine learning (ML). Synthetic data generation is becoming essential, but current generative models often miss TEM-specific noise, structural detail, and stochastic variability crucial for evaluation. We present a Denoising Diffusion Probabilistic Model (DDPM) framework for synthetic TEM image generation under extreme data scarcity. A progressive patch-based training strategy scales from low-resolution patches to full images, enabling from-scratch training with only 15 samples. We integrate a custom TrivialAugment adaptation, cross-process domain transfer, classifier guidance, and RePaint-style inpainting, culminating in full-image generation that preserves global structural and spatial relationships in compliance with FAB metrology requirements. Beyond synthesis, we repurpose DDPM feature representations for segmentation, partitioning encoder feature maps to obtain coherent region masks. Our synthetic images achieve up to MS-SSIM > 0.98 and qualitative expert assessment consistent with structural similarity results, facilitating downstream ML training for defect detection, segmentation, and metrology while preserving statistical and physical realism.

0

eess.IV 2026-06-24

AI framework automates uterine MRI analysis during scans

by Deepak Bhatia, Saad Ahmad +8 more

Female-RHINO: A Real-Time Scanner-Integrated Framework for Automated Quantitative Uterine MRI Analysis and Structured Reporting

Deep learning models on multi-center data deliver uterus and fibroid segmentation plus reports in under 70 seconds.

abstract click to expand

Standardized assessment of uterine MRI remains challenging due to anatomical variability, observer dependence, and the lack of workflow-integrated automated analysis tools. This work presents Female-RHINO: (R)eproductive (H)ealth (I)maging A(N)alysis T(O)ol, a real-time AI-assisted framework for automated quantitative uterine MRI analysis and structured reporting during image acquisition. We present an end-to-end system that integrates inline communication with the MRI scanner and deep learning-based analysis to derive quantitative uterine biomarkers from sagittal T2-weighted pelvic MRI. The framework combines segmentation and anatomical landmark detection models trained and evaluated on more than 500 multi-center datasets spanning diverse protocols, vendors, and patient populations. It performs volumetry, detects and quantifies common incidental findings such as fibroids and Nabothian cysts, and extracts six anatomical landmarks for biometric assessment. Results are compiled into a structured clinician-oriented report with integrated visualizations, without manual interaction. Evaluation on independent retrospective and prospective cohorts demonstrated robust performance across varying acquisition settings. Mean Dice similarity coefficients were 0.82 for the uterus and 0.80 for fibroids, with lower but consistent agreement for Nabothian cysts. Landmark detection achieved a mean radial error of 3.7 mm. End-to-end processing was completed in under 70 seconds, enabling availability of results during the ongoing scan. Prospective deployment yielded immediate, standardized, and reproducible analyses supported by inter-observer agreement. The proposed system enables real-time scanner-integrated AI for automated uterine MRI analysis and reporting, with potential to improve standardization, efficiency, and clinical workflow in pelvic imaging.

0

eess.IV 2026-06-24

Sediment-specific models retrieve mining site soil moisture at 3.7-5% error

by Alireza Hamedianfar, Oleg Antropov +6 more

High Resolution Sediment-Specific Surface Soil Moisture Retrieval Using Sentinel-1 Time Series and Auxiliary Data

Sentinel-1 time series plus auxiliary data and sediment type reach R2 of 0.90 with tree ensembles at a Finnish limestone quarry.

abstract click to expand

In this study, we examine the potential of continuous ground moisture monitoring over a mining site using a combination of in-situ soil moisture sensors and multi-sensor SAR images. We focus on assessing and improving methodologies for retrieval of surface soil moisture, i.e. ground moisture, from SAR measurements focusing on detailed in situ reference observations for several key geomaterials, i.e. sediments, typical in the study site. The mining site represents a limestone quarry locate in the southeastern Finland. Our hypothesis is that sediment-specific well-calibrated models can be instrumental in improving soil moisture retrieval under different weather conditions to produce spatially explicit soil moisture estimates at high resolution compared to baseline approaches. Studied SAR data are represented by Copernicus Sentinel-1 C-band images, while auxiliary datasets include optical Sentinel-2 data. Reference data were collected using IoT enabled capacitance sensors. The examined machine learning methods include Xgboost, LightGBM, RFs, linear regression and k-nearest neighbors regression. The best performance was achieved with the most comprehensive feature set which combines Sentinel-1 backscatter, time-series based soil moisture indices, Sentinel-2 optical, topographic, and temperature predictors. In the best sediment-area-level configurations, RMSE decreased to 0.037-0.050 m^3 m^(-3) (3.7-5.0 volumetric % points), with R^2 values reaching 0.90. Tree-based ensemble methods, especially LightGBM, RF, and XGBoost, provided the most accurate and stable predictions. Accuracy varied by sediment texture, with the lowest errors for clay and organic soil and higher errors for flotation sand and gravel. Adding sediment information improved Sentinel-1-only retrievals by more than 2 vol-%, but provided little additional benefit when richer multi-source feature sets were used.

1 0

0

eess.IV 2026-06-24

Dual-edge graph fuses vessel-lesion and biomarker data for DR grading

by Inam Ullah, Imran Razzak +1 more

A Dual Edge Spatial Jacobian Image Graph for Interpretable Diabetic Retinopathy Grading

Spatial and Jacobian branches combine four streams on 2910 APTOS images to reach 0.83 quadratic weighted kappa

abstract click to expand

Automated diabetic retinopathy (DR) grading from colour fundus photographs can achieve strong predictive performance, but clinical interpretation requires more than an image-level label. It requires understanding how lesion evidence is distributed around retinal vessels and how this evidence relates to quantitative vascular biomarkers. We present a dual-edge spatial-Jacobian image graph for interpretable DR grading. Each fundus image is represented as a graph node with four aligned evidence streams: AutoMorph vessel information ($X_1$), DR-XAI-style lesion evidence maps ($X_2$), a 128-dimensional lesion-based contrastive image embedding ($X_3$), and AutoMorph morphometric biomarkers ($X_4$). The spatial edge branch ($X_{12}$) encodes vessel-lesion geometry, while the Jacobian branch ($X_{34}$) models embedding-biomarker sensitivity. Lightweight two-token attention fuses both edge families into a final image graph. On 2,910 matched non-augmented APTOS images, the full graph achieves 0.8076 accuracy, 0.8312 quadratic weighted kappa, 0.5915 macro-F1, and 0.9330 adjacent-grade accuracy; referable DR reaches 0.9055 accuracy and 0.9711 AUROC. The framework is positioned as an explainable representation-learning tool for lesion-biomarker hypothesis generation, rather than as a deployment-ready clinical classifier. The code is available at https://github.com/Inamullah-Colab/dual-edge-dr-graph-xai.

0

eess.IV 2026-06-24

Leakage-free split drops leukemia AUROC by 0.04 on C-NMC 2019

by Nisreen Albzour

A Leakage-Aware Comparative Benchmark of Machine Learning, Deep Learning, and Transformer Models for Reliable Leukemia Detection

EfficientNet-B1 reaches 0.913 AUROC under patient-disjoint evaluation while random splits inflate results even for frozen models.

abstract click to expand

Automated classification of acute lymphoblastic leukemia (ALL) from peripheral blood smear images has often reported near-perfect performance on the C-NMC 2019 dataset. We show that such results can be inflated by patient-level data leakage caused by random image-level partitioning, where cells from the same subject may appear in both training and test folds. We establish a leakage-aware benchmark under a strict subject-disjoint protocol, comparing LightGBM, RBF-SVM, EfficientNet-B0, EfficientNet-B1, and ViT-Tiny. Models are developed using three subject-disjoint folds from 73 subjects and evaluated on an external preliminary-phase test set of 1,867 images from 28 unseen subjects with zero patient overlap. Beyond discrimination, we assess calibration using expected calibration error, Brier score, and temperature scaling. Under honest evaluation, EfficientNet-B1 achieves the best performance, with AUROC 0.913, sensitivity 0.87, specificity 0.80, and calibrated ECE 0.024. Frozen-feature classifiers and ViT-Tiny show high sensitivity but poor specificity, indicating a tendency to over-predict the malignant class. A random-versus-subject-disjoint ablation shows that random splitting inflates AUROC by about 0.04 even in the conservative frozen-feature setting. These findings caution against image-level evaluation on C-NMC 2019 and provide a reproducible, calibration-aware benchmark for future work.

0

cs.CV 2026-06-24

Foundation model outperforms on new flood mapping

by Vladyslav Polushko, Tilman Bucher +4 more

Flood Mapping from RGB imagery using a Vision Foundation Model

It leads baselines in zero-shot transfer across events and reaches near-full accuracy with the least new labels.

abstract click to expand

Timely, high-resolution maps of flood extent around settlements are essential for emergency response and damage assessment. We consider airborne RGB imagery for flood mapping as it can be collected rapidly at low cost. To produce flood maps, deep learning models for water segmentation are often used. CNN based and small vision transformer models are used. However, they need much data for adaptation to a change of scenery, i.e., another flooding event. Vision foundation models or large vision transformers are known to generalize across domains. Recently, foundation models for Earth observation became available. They are pretrained on satellite data, whose spatial resolution, viewing geometry, and radiometry differ from nadir RGB imagery. Thus, adaptation is required. We investigate how a satellite-pretrained Earth observation foundation model can be adapted to centimeter-scale floodwater mapping from RGB imagery. Specifically, we fine-tune a model we call Prithvi-2.0-UPN consisting of the Prithvi-EO-2.0-600M Vision Transformer combined with a UPerNet decoder for binary water segmentation on two RGB datasets (BlessemFlood21, NeuenahrFlood). In a first experiment we observe that Prithvi-2.0-UPN reaches state-of-the-art results on BlessemFlood21 and NeuenahrFlood, when trained on their datasets. In a second experiment we show that Prithvi-2.0-UPN performs better than state-of-the-art baseline models for transfer to a new flood event (trained on BlessemFlood21, tested on NeuenahrFlood) in a zero-shot setting. However, the performance indicates room for improvement. In this respect, we investigate in a third experiment how performance improves when further fine-tuning the models with small shares of NeuenahrFlood training data: Prithvi-2.0-UPN improves the fastest and reaches almost the performance level when fully trained on NeuenahrFlood, indicating transfer capabilities.

0

eess.IV 2026-06-23

RL framework grounds 3D CT reports to key slices and cuts hallucinations

by Sijing Li, Zhongwei Qiu +7 more

E-MRL: Cross-view Aligned Evidence-driven Multimodal Reinforcement Learning for Reliable 3D Tumor Analysis

A cross-view reward checks that selected slices support the generated diagnosis, improving accuracy over text-only training.

abstract click to expand

While Vision-Language Models (VLMs) show great promise in volumetric medical report generation, they frequently suffer from visual hallucinations and a lack of grounding in 3D CT data. Current Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) strategies typically optimize text fidelity alone, essentially rewarding correct diagnoses derived from language priors rather than genuine visual perception. To address this, we propose cross-view aligned Evidence-driven Multimodal Reinforcement Learning (Evidence-MRL, noted as E-MRL), a reliable RL reasoning framework that formulates the generation process as a Markov Decision Process of "diagnosis-localization-verification". Unlike standard approaches, our model is explicitly trained to identify a "key evidence slice" alongside the global diagnostic report, grounding its findings in verifiable visual evidence. Crucially, we introduce a novel cross-view consistency reward, which validates the semantic alignment between the golden-standard report and a local visual re-query of the selected key slice, providing additional rewards for correctly-localized reasoning. Experiments on large-scale 3D CT tumor datasets demonstrate that E-MRL significantly reduces hallucinations and improves diagnostic accuracy compared to SFT and RL baselines, offering a clinically interpretable solution for visually-grounded and tumor analysis.

0

eess.IV 2026-06-23

Image translation enables heart chamber segmentation on non-contrast CT

by Jing Wang, Tong Yu +6 more

Promise and challenges of heart chamber segmentation from non-contrast CT scans using contrastive unpaired image translation: a feasibility study

ChameleonNet achieves Dice scores over 0.91 on synthetic images and volume correlations above 0.82 on real scans without non-contrast labels

abstract click to expand

Purpose: To evaluate the feasibility and challenges of heart chamber segmentation from non-contrast CT scans using contrastive unpaired image translation and deep learning-based segmentation. Approach: We developed ChameleonNet, a framework utilizing the Contrastive Unpaired Translation (CUT) network with decoupled contrastive learning (DCL) loss to synthesize non-contrast CT from contrast CT scans. Using annotations of four heart chambers (left atrium (LA), left ventricle (LV), right atrium (RA), and right ventricle (RV)) from contrast scans, we trained a Hausdorff distance loss-enhanced nnU-Net on synthesized non-contrast images. The translation model was trained with 35,538 contrast-enhanced and 37,197 non-contrast CT slices. The segmentation model was trained with 292 synthesized non-contrast scans. Performance was evaluated using Dice similarity coefficient (DSC) and 95th Hausdorff distance (HD95) on 36 synthesized non-contrast scans, and volume agreement on 36 real non-contrast CT scans was assessed using Pearson correlation, mean absolute percentage error (MAPE), and mean percentage error (MPE). Results: The segmentation model achieved DSC of 0.94 (0.01), 0.91 (0.04), 0.92 (0.03), 0.93 (0.02), and HD95 of 3.63 (1.49), 5.74 (4.08), 5.18 (1.77), 5.51 (3.21) mm on synthesized non-contrast images for LA, LV, RA, and RV, respectively. On real non-contrast CT scans, Pearson correlations were 0.93, 0.82, 0.87, and 0.89 (all p<0.001), with MAPE ranging from 9.22% to 20.79%, and MPE ranging from -12.52% to 4.67%. Conclusions: ChameleonNet demonstrated feasibility for heart chamber segmentation from non-contrast CT without manual non-contrast annotations. However, volume errors, particularly for LV and RV, indicate that further refinement and validation are needed before clinical use.

0

cs.CV 2026-06-23

3B model unifies counting and count-faithful image generation

by Anindya Mondal, Sauradip Nag +1 more

ABACUS: Adapting Unified Foundation Model for Bridging Image Count Understanding and Generation

Adapting a foundation model with zooming, boundary policies, and self-critique achieves SOTA on seven benchmarks without extra training.

abstract click to expand

ABACUS is a unified vision-language model that handles object counting, crowd counting, referring-expression counting, and count-faithful image generation without any benchmark-specific training required. Our model is built on existing 3B-parameter unified foundation model and is adapted for object localization tasks using three key innovations: density-aware adaptive zooming with objectness maps for spatial grounding; a boundary-aware count policy via GRPO to eliminate crop-boundary errors; and a cycle-consistent GRPO strategy where the understanding branch self-critiques generated outputs, closing the understanding-generation gap without any external annotations. ABACUS achieves state-of-the-art results across seven benchmarks, outperforming both task-specific specialists and larger generalist models.

0

eess.IV 2026-06-23

NGPS uses guide patches to pull raw signals from misaligned neighbors

by Jaehyun Cho, Youngjoon Yoo

NGPS: Structure-Preserving Self-Supervised Denoising via Neighbor-Guided Patch Sampling

Matching structure on a guide image while retrieving raw neighbor values builds pseudo targets without registration.

abstract click to expand

Neighboring-slice self-supervised denoising is attractive for volumetric medical imaging, yet inter-slice misalignment breaks anatomical correspondence and often yields ghosting and blurred margins when adjacent slices are used naively as targets. We propose Neighbor-Guided Patch Sampling (NGPS), a lightweight framework that constructs neighboring supervision under local inter-slice misalignment without explicit registration. To avoid learning from misleading targets, prior methods commonly mask discrepant regions, but this stabilizes training at the cost of leaving a non-trivial portion of neighboring evidence unexploited, particularly around high-frequency anatomical boundaries. NGPS addresses this by decoupling structure matching from signal retrieval: for each masked location, it searches a local neighborhood for structurally similar candidate patches using a simple guide image (e.g., fast bilateral filtering), while retrieving the supervision signal directly from the raw noisy neighbor at the matched coordinates. By matching on a noise-attenuated guide while retrieving raw values from neighboring slices, NGPS constructs local pseudo targets without a learned registration module. Across the evaluated CT and synthetic-Rician MRI settings, NGPS improves fidelity and structure-sensitive metrics. Code is available at https://github.com/cv-cho/NGPS .

0

eess.IV 2026-06-23

Tabular radiomics model matches image foundation models for glioma IDH prediction

by Nathan Hollet, Elise Robinson +4 more

A Benchmark of (MRI-) Foundation Models to Predict IDH Mutational Status in Glioma

Benchmark on four public cohorts and one external set finds TabPFN at 0.92 AUROC while MRI-specific encoders lag behind general image models

abstract click to expand

Non-invasive prediction of glioma molecular status from routine magnetic resonance imaging (MRI) has shown promising performance, but model generalization remains challenging given small-scale matched imaging-genomic datasets. Foundation models may address this bottleneck, but a comprehensive benchmark is needed to establish the impact of diverse architectures, pre-training domains, and objectives. Given the use case of isocitrate dehydrogenase (IDH) mutation prediction from FLAIR and post-contrast T1 MRIs, we compared four image-based foundation models, BrainIAC, MRI-CORE, BiomedCLIP, and BrainDINO, against radiomics-based TabPFN and logistic regression baselines. Prediction performance and calibration were assessed across four public adult glioma cohorts and an external post-treatment cohort. Within-cohort, TabPFN matched or outperformed all visual encoders, achieving 0.92 (0.03) AUROC and 0.74 (0.17) AUPRC (mean (SD) across all datasets). Among visual encoders, BiomedCLIP performed best (0.85 (0.08) AUROC), with BrainDINO competitive (0.82 (0.09) AUROC), while MRI-specific encoders (BrainIAC, MRI-CORE) consistently underperformed. Cross-cohort transfer showed moderate AUROC degradation but stronger AUPRC sensitivity to prevalence shifts. On the external cohort, BiomedCLIP achieved the highest AUROC (0.74 (0.07)), whereas TabPFN provided superior calibration (Expected Calibration Error 0.07 (0.01)). These results indicate that representation modality and evaluation context critically influence foundation-model performance in MRI-based molecular prediction. Tabular foundation models on radiomic features provide a strong, well-calibrated baseline, while image foundation models may offer complementary value under clinically distinct distribution shifts. Code available at https://github.com/nathanhollet/idh-status-prediction

0

eess.IV 2026-06-23

Event camera methods split into dense grids or sparse events

by Hongwei Ren, Youxin Jiang +2 more

A Systematic Survey on Event Camera Representation Learning

Survey shows how each approach trades structural regularity for temporal fidelity and sparsity preservation

abstract click to expand

Event cameras offer distinctive advantages, including microsecond-level latency and high dynamic range, rendering them promising for challenging perception tasks. Inspired by biological vision, they output asynchronous and sparse event streams rather than dense image frames, creating a fundamental mismatch with mainstream neural networks. This survey reviews recent advances in event camera representation learning from the perspective of converting raw event streams into learnable representations. We organize existing methods into two main categories: (1) dense-based representations, which transform raw event streams into regular grid-like structures to leverage mature RGB backbones and multimodal fusion pipelines, and (2) sparse-based representations, which retain events as discrete spatio-temporal structures to preserve fine-grained temporal dynamics and data sparsity. This representation-centric organization clarifies how different representations balance structural regularity, temporal fidelity, sparsity preservation, and architectural compatibility. For each category, we examine the underlying design choices, modeling principles, and task-level implications.We further summarize standard benchmarks and evaluation settings across representative high-level perception and low-level vision tasks. Finally, we discuss open problems and outline future research directions toward more efficient, scalable, and robust event-based perception systems.

0

eess.IV 2026-06-23

QP constraint keeps skin-disease ViT accuracy at 93.8 percent with 29.5 percent less redun

by Haibiao Li, Di Lin +4 more

IViT: A Novel Interpretable Visual Transformer for Skin Disease Detection

Core activations align with clinical lesion areas across six datasets while staying within 0.21 percent of baseline performance.

abstract click to expand

The clinical diagnosis of skin diseases is susceptible to interference from inter-class similarity of skin lesions, and over-reliance on clinicians'experience easily leads to subjective bias. Although existing deep learning aided diagnosis methods achieve competitive accuracy, they suffer from the black-box opacity of Vision Transformer (ViT) and poor adaptability to medical few-shot scenarios. Moreover, mainstream explainable algorithms generally face the bottleneck of significant accuracy degradation when improving interpretability. This paper proposes an interpretable ViT (IViT) constrained by Quadratic Programming (QP). The introduced pre-trained transfer learning adapts to few-shot feature extraction. A discrete QP feature selection framework is constructed to screen generic and discriminative features consistent with clinical diagnostic logic. A multi-objective loss function is designed to reduce feature redundancy and optimize activation distribution while preserving classification performance. Experimental results on six standard skin disease datasets show that IViT achieves an accuracy of 93.80%, only 0.21% lower than the baseline, with feature redundancy reduced by 29.5%. Its core activation regions are consistent with clinically concerned lesion areas. The proposed model balances accuracy and interpretability, providing a reliable solution for the clinical deployment of few-shot intelligent skin disease diagnosis.

0