REVIEW 15 cited by
Synscapes: A Photorealistic Synthetic Dataset for Street Scene Parsing
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
Synscapes: A Photorealistic Synthetic Dataset for Street Scene Parsing
read the original abstract
We introduce Synscapes -- a synthetic dataset for street scene parsing created using photorealistic rendering techniques, and show state-of-the-art results for training and validation as well as new types of analysis. We study the behavior of networks trained on real data when performing inference on synthetic data: a key factor in determining the equivalence of simulation environments. We also compare the behavior of networks trained on synthetic data and evaluated on real-world data. Additionally, by analyzing pre-trained, existing segmentation and detection models, we illustrate how uncorrelated images along with a detailed set of annotations open up new avenues for analysis of computer vision systems, providing fine-grain information about how a model's performance changes according to factors such as distance, occlusion and relative object orientation.
Forward citations
Cited by 15 Pith papers
-
SpatialBench: Is Your Spatial Foundation Model an All-Round Player?
SpatialBench evaluates 41 spatial foundation models across 6 paradigms and 5 task suites, finds they are not all-round players, and introduces the DA-Next-5M dataset plus DA-Next baseline model.
-
Honey, I Shrunk the Arc de Triomphe!
Introduces MetricScenes dataset with metric grounding from geo-tags and stereo, plus Poisson depth completion, showing fine-tuned MoGe-2 reduces scale-collapse in open scenes.
-
Honey, I Shrunk the Arc de Triomphe!
MetricScenes dataset from web photos and stereo imagery, plus a two-stage Poisson depth completion method, allows fine-tuning MoGe-2 to mitigate scale-collapse in metric monocular geometry while preserving benchmark p...
-
CARD: A Multi-Modal Automotive Dataset for Dense 3D Reconstruction in Challenging Road Topography
CARD is a new multi-modal driving dataset delivering ~500K dense depth pixels per frame from challenging road topographies using stereo cameras and fused LiDARs over 110 km.
-
Multi-Modal Guided Multi-Source Domain Adaptation for Object Detection
MS-DePro achieves state-of-the-art performance on multi-source domain adaptation benchmarks for object detection by using depth-guided region proposals and multi-modal alignment of learnable text embeddings.
-
MULTI: Disentangling Camera Lens, Sensor, View, and Domain for Novel Image Generation
MULTI uses two-stage textual inversion to disentangle camera lens, sensor, view, and domain factors for novel image generation, supporting dataset extension and ControlNet modifications on the new DF-RICO benchmark.
-
The Power of Light: Improving Synthetic-to-Real Domain Adaptation through Physically-Based Indirect Illumination
Empirical study shows complex indirect lighting and background variability in synthetic data improve YOLOv12 object detection transfer to real industrial scenes over direct lighting baselines.
-
Unsupervised Collaborative Domain Adaptation for Driving Scene Parsing
UCDA transfers complementary knowledge from multiple source models to a target model via prototype-based reliability estimation and two-stage collaborative refinement for source-free driving scene parsing.
-
Generating Realistic Safety-Critical Scenarios for Vehicle-Pedestrian Interactions
A three-stage framework pre-trains multi-agent RL agents on real safety-critical data, refines them via online learning in CARLA, and generates the VPSCI dataset of over 198,000 realistic vehicle-pedestrian interactio...
-
DriveCtrl: Conditioned Sim-to-Real Driving Video Generation
DriveCtrl is a depth-conditioned controllable framework that generates realistic driving videos from simulation while preserving annotations and scene dynamics.
-
Syn4D: A Multiview Synthetic 4D Dataset
Syn4D is a new multiview synthetic 4D dataset supplying dense ground-truth annotations for dynamic scene reconstruction, tracking, and human pose estimation.
-
MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details
MoGe-2 recovers metric-scale 3D point maps with fine details from single images via data refinement and extension of affine-invariant predictions.
-
Large Depth Completion Model from Sparse Observations
LDCM achieves state-of-the-art metric depth completion from sparse observations by combining foundation-model initialization with a point-map regression head that removes the need for camera intrinsics.
-
AtteConDA: Attention-Based Conflict Suppression in Multi-Condition Diffusion Models and Synthetic Data Augmentation
AtteConDA adds attention-based conflict suppression to multi-condition diffusion models so that generated driving-scene images retain richer structural cues from the original annotations.
-
How much real data do we actually need: Analyzing object detection performance using synthetic and real data
Synthetic data can partially substitute for real data in object detection training, with performance tied to domain similarity and the volume of real data included.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.