REVIEW 30 cited by
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Noise2Noise: Learning Image Restoration without Clean Data
read the original abstract
We apply basic statistical reasoning to signal reconstruction by machine learning -- learning to map corrupted observations to clean signals -- with a simple and powerful conclusion: it is possible to learn to restore images by only looking at corrupted examples, at performance at and sometimes exceeding training using clean data, without explicit image priors or likelihood models of the corruption. In practice, we show that a single model learns photographic noise removal, denoising synthetic Monte Carlo images, and reconstruction of undersampled MRI scans -- all corrupted by different processes -- based on noisy data only.
Forward citations
Cited by 30 Pith papers
-
$\Omega$: Operator-based Mixture Ensemble for Generative Assimilation
Ω is a generative assimilation method that learns residual discrepancies from ensemble data using a conditional Gaussian baseline, then reconstructs full non-Gaussian posteriors via Gaussian mixtures and annealed Lang...
-
Pyramid Self-Contrastive Learning for Single-shot Test-time Ultrasound Image Denoising
A2A achieves one-shot ultrasound denoising via pyramid self-contrastive learning on sub-aperture signals to disentangle anatomy from noise, yielding large SNR and CNR gains in simulations and in vivo scans.
-
FrequencyCT: Frequency Domain Self-supervised Low-dose CT Denoising
FrequencyCT generates pseudo-labels via regional low-frequency anchoring, phase-preserving modulation, and high-frequency mask perturbation for self-supervised low-dose CT denoising.
-
FrequencyCT: Frequency Domain Self-supervised Low-dose CT Denoising
FrequencyCT is a frequency-domain zero-shot self-supervised method that creates pseudo-samples via low-frequency anchoring, phase-preserving high-frequency perturbations, and signal-correlated truncation for low-dose ...
-
A Mixture of Experts Foundation Model for Scanning Electron Microscopy Image Analysis
A mixture-of-experts transformer foundation model pretrained on diverse SEM images enables generalization across materials and outperforms SOTA on unsupervised defocus-to-focus restoration.
-
Towards a Unified Theoretical Framework for Splitting-based Self-Supervised MRI Reconstruction
UNITS framework proves self-supervised splitting risk in MRI reconstruction is a weighted supervised risk, yielding identical Bayes-optimal predictors and relating training residuals to prediction bias.
-
BiDeMem: Bidirectional Degradation Memory for Explainable Image Restoration
BiDeMem retrieves compact memory slots via a query from restoration features to jointly improve restoration quality and provide a falsifiable degradation explanation path in a controlled NAFNet multi-degradation setting.
-
Poisson2Gaussian: Noise Gaussianization to Enhance Image Denoising
Poisson2Gaussian converts Poisson-mixed noise to i.i.d. Gaussian noise via density matching and pairs it with an unbiased denoising framework to improve performance without paired clean data.
-
Regularized joint reconstruction and slab combination for accelerated three-dimensional multi-slab diffusion-weighted imaging using multi-scale energy models
EPEN jointly reconstructs diffusion-weighted images and estimates slab profiles from undersampled 3D multi-slab k-space using a bilinear model, CNN deep energy prior, and alternating minimization to suppress artifacts.
-
A Deep Learning Iterative Framework for Sentinel-1 Stripmap Enhancement Based on Azimuth Doppler Decomposition
Self-supervised iterative DL framework for S1 SM SAR enhancement via azimuth subaperture decomposition outperforms MERLIN on PSNR and SSIM.
-
Internally Referenced Low-Light Enhancement
Introduces self-supervised LLIE using internal low-frequency pseudo ground-truth, dual-domain structural constraints, and gain-adaptive modulation to achieve superior noise suppression and detail preservation.
-
Physen-Noise2Noise: Physics-Guided Self-Supervised Defocus Deblurring with Bias Correction under Low-Light Conditions
Physen-Noise2Noise is a physics-guided self-supervised framework for defocus deblurring that models and corrects biased noise using frequency-domain constraints and multi-frame initialization.
-
RDDM: A Residual-Driven Drifting Model for High-Fidelity Low-Dose CT Denoising
RDDM introduces a residual drifting field with attractive and repulsive forces to achieve one-step supervised denoising of low-dose CT, reporting superior PSNR, SSIM, FID of 5.87, and 15 ms inference time.
-
TwinSpecNet: Extending APOGEE's chemical reach to low-S/N spectra via empirical paired learning
TwinSpecNet uses empirical paired learning on spectral twins to denoise low-S/N APOGEE spectra and predict stellar parameters and abundances with lower scatter than the standard pipeline.
-
TM-BSN: Triangular-Masked Blind-Spot Network for Real-World Self-Supervised Image Denoising
TM-BSN introduces triangular-masked convolutions that align blind spots with diamond-shaped noise correlations from camera demosaicing, enabling stronger self-supervised denoising at full resolution without downsampling.
-
Progressive $\mathcal{J}$-Invariant Self-supervised Learning for Low-Dose CT Denoising
A progressive J-invariant self-supervised learning framework for low-dose CT denoising outperforms prior self-supervised methods and matches some supervised ones on the Mayo dataset.
-
Linear Attention Based Deep Nonlocal Means Filtering for Multiplicative Noise Removal
LDNLM replaces the quadratic similarity and averaging steps of nonlocal means with deep convolutional feature extraction and linear attention operations to produce a linear-complexity denoiser for multiplicative noise...
-
Evaluating Similitude and Robustness of Deep Image Denoising Models via Adversarial Attack
Denoising-PGD attack exposes shared adversarial samples across non-blind, blind, plug-and-play and unfolding denoisers, yielding a robustness similitude metric that ranks data-driven non-blind models as most robust.
-
Self-supervised Hyperspectral Image Restoration using Separable Image Prior
A self-supervised separable CNN trained on data synthesized from a single degraded hyperspectral image achieves restoration without clean reference images.
-
A Zero-Shot Deep Image Prior Framework for Denoising and Deconvolution in Fluorescence Microscopy
SDIP is a zero-shot DIP method using sequential autoencoding regularization for denoising followed by Richardson-Lucy-guided DIP for deconvolution, reporting improved SNR and resolution on BioSR cellular structures.
-
Enabling self-supervised learned primal dual with Noise2Inverse
N2I-LPD adapts Noise2Inverse to Learned Primal-Dual for self-supervised training of iterative CT operators without ground-truth data, showing improved quality over classical methods and U-Net baselines.
-
Physics-Guided Self-Supervised Statistical Residual Learning for Sonar Despeckling with Improved Generalization
A self-supervised neural network for sonar despeckling enforces multiplicative speckle statistics via log-domain residual consistency and achieves state-of-the-art performance with strong cross-dataset generalization.
-
Pyramid Self-Contrastive Learning for Single-shot Test-time Ultrasound Image Denoising
PSCL separates anatomy from noise in pyramid latent spaces using self-contrastive learning on single-shot ultrasound data, yielding reported SNR gains of 69.3% (simulation) and 84.8% (in vivo) plus CNR gains.
-
Machine Learning Enhanced Laser Spectroscopy for Multi-Species Gas Detection in Complex and Harsh Environments
Machine learning methods including denoising autoencoders, unsupervised interference mitigation, blind source separation, and certifiable classification are developed and experimentally validated to improve multi-spec...
-
AstroSURE: Learning to Remove Noise from Astronomical Images Without Ground Truth Data
Unsupervised denoising methods improve faint-source detection in astronomical images from HST and CFHT, with better performance when models are initialized on similar-domain data.
-
Progressive $\mathcal{J}$-Invariant Self-supervised Learning for Low-Dose CT Denoising
A new progressive J-invariant self-supervised denoising method for LDCT that uses step-wise blind-spot enforcement and controlled noise injection outperforms prior self-supervised approaches on the Mayo dataset.
-
Dynamic Weight-based Temporal Aggregation for Low-light Video Enhancement Under Extreme Noise
DWTA-Net is a two-stage recurrent neural network for low-light video enhancement that combines Mamba-based local restoration with dynamic optical-flow-guided temporal aggregation and a texture-adaptive loss to suppres...
-
A Survey on Diffusion Models for Inverse Problems
A survey that introduces taxonomies for categorizing pre-trained diffusion model methods applied to inverse problems and analyzes their connections and challenges.
-
A Positron Range Correction with Texture Preservation Framework in PET Imaging
PRC-TP combines an nnFormer network trained on Monte Carlo simulations with Model-consistent Texture Re-Injection to correct positron range effects in 82Rb PET while restoring acquisition-consistent texture.
-
Forgive or forget: Understanding the context of hate in audio retrieval systems
Introduces a model-agnostic causal debiasing method using a sentiment-controlled mediator and two variants (Forgive, Forget) that reduces toxicity in audio retrieval with minimal accuracy loss.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.