mlsanityData to 14 Oct 2026

OpenStereo: A Comprehensive Benchmark for Stereo Matching and Strong Baseline

arXiv 2312.00343 ↗First posted 1 Dec 2023cs.CVcited by 30

Not on the map. Why?

Abstract (arXiv)

Stereo matching aims to estimate the disparity between matching pixels in a stereo image pair, which is important to robotics, autonomous driving, and other computer vision tasks. Despite the development of numerous impressive methods in recent years, determining the most suitable architecture for practical application remains challenging. Addressing this gap, our paper introduces a comprehensive benchmark focusing on practical applicability rather than solely on individual models for optimized performance. Specifically, we develop a flexible and efficient stereo matching codebase, called OpenStereo. OpenStereo includes training and inference codes of more than 10 network models, making it, to our knowledge, the most complete stereo matching toolbox available. Based on OpenStereo, we conducted experiments and have achieved or surpassed the performance metrics reported in the original paper. Additionally, we conduct an exhaustive analysis and deconstruction of recent developments in stereo matching through comprehensive ablative experiments. These investigations inspired the creation of StereoBase, a strong baseline model. Our StereoBase ranks 1st on SceneFlow, KITTI 2015, 2012 (Reflective) among published methods and achieves the best performance across all metrics. In addition, StereoBase has strong cross-dataset generalization. Code is available at urlhttps://github.com/XiandaGuo/OpenStereo.

Key facts. Cited by 30 papers in the map (data through 14 Oct 2026). Builds on 56 of its 81 references that are in the map. First posted on arXiv 1 Dec 2023.

Builds on

56 of 81 references.

References · 56

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  5. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
  6. 2018DARTS: Differentiable Architecture Searchcited by 1,798
  7. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,385
  8. 2017Random Erasing Data Augmentationcited by 1,239
  9. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,162
  10. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,135
  11. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,059
  12. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 881
38 more
  1. 2016ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Camerascited by 806
  2. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 787
  3. 2016FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networkscited by 784
  4. 2018Pyramid Stereo Matching Networkcited by 489
  5. 2019Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matchingcited by 417
  6. 2019AutoML: A Survey of the State-of-the-Artcited by 390
  7. 2017End-to-End Learning of Geometry and Context for Deep Stereo Regressioncited by 360
  8. 2021RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matchingcited by 353
  9. 2019GA-Net: Guided Aggregation Net for End-to-end Stereo Matchingcited by 244
  10. 2019Group-wise Correlation Stereo Networkcited by 235
  11. 2020AANet: Adaptive Aggregation Network for Efficient Stereo Matchingcited by 202
  12. 2022Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlationcited by 197
  13. 2020Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective with Transformerscited by 190
  14. 2023Iterative Geometry Encoding Volume for Stereo Matchingcited by 190
  15. 2020Hierarchical Neural Architecture Search for Deep Stereo Matchingcited by 166
  16. 2022CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flowcited by 166
  17. 2021CFNet: Cascade and Fused Cost Volume for Robust Stereo Matchingcited by 154
  18. 2015Stereo Matching by Training a Convolutional Neural Network to Compare Image Patchescited by 151
  19. 2022Attention Concatenation Volume for Accurate and Efficient Stereo Matchingcited by 130
  20. 2019Hierarchical Deep Stereo Matching on High-resolution Imagescited by 126
  21. 2023RepViT: Revisiting Mobile CNN From ViT Perspectivecited by 123
  22. 2021MPViT: Multi-Path Vision Transformer for Dense Predictioncited by 122
  23. 2021SMD-Nets: Stereo Mixture Density Networkscited by 120
  24. 2019DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatchcited by 114
  25. 2015Learning to Compare Image Patches via Convolutional Neural Networkscited by 109
  26. 2019Domain-invariant Stereo Matching Networkscited by 109
  27. 2018StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Predictioncited by 88
  28. 2018SegStereo: Exploiting Semantic Information for Disparity Estimationcited by 88
  29. 2022OpenGait: Revisiting Gait Recognition Toward Better Practicalitycited by 85
  30. 2021MobileStereoNet: Towards Lightweight Deep Networks for Stereo Matchingcited by 82
  31. 2018Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimationcited by 69
  32. 2019Adaptive Unimodal Cost Volume Filtering for Deep Stereo Matchingcited by 55
  33. 2018Anytime Stereo Image Depth Estimation on Mobile Devicescited by 54
  34. 2021Correlate-and-Excite: Real-Time Stereo Matching via Guided Cost Volume Excitationcited by 47
  35. 2022Revisiting Domain Generalized Stereo Matching Networks from a Feature Consistency Perspectivecited by 46
  36. 2020Bi3D: Stereo Depth Estimation via Binary Classificationscited by 34
  37. 2021Local Similarity Pattern and Cost Self-Reassembling for Deep Stereo Matching Networkscited by 32
  38. 2020FADNet: A Fast and Accurate Network for Disparity Estimationcited by 31

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 8; 2025: 13; 2026: 9.

30 papers.

Sort:

By area:

  1. 2025DEFOM-Stereo: Depth Foundation Model Based Stereo Matchingcited by 52
  2. 2025Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformerscited by 51
  3. 2024SURDS: Benchmarking Spatial Understanding and Reasoning in Driving Scenarios with Vision Language Modelscited by 29
  4. 2024LightStereo: Channel Boost Is All You Need for Efficient 2D Cost Aggregationcited by 28
  5. 2024Playing to Vision Foundation Model's Strengths in Stereo Matchingcited by 23
  6. 2025BANet: Bilateral Aggregation Network for Mobile Stereo Matchingcited by 12
  7. 2024Instruct Large Language Models to Drive like Humanscited by 11
  8. 2024ClearDepth: Enhanced Stereo Perception of Transparent Objects for Robotic Manipulationcited by 9
  9. 2024Stereo Anything: Unifying Zero-shot Stereo Matching with Large-Scale Mixed Datacited by 5
  10. 2025Lite Any Stereo: Efficient Zero-Shot Stereo Matchingcited by 4
  11. 2024MaskFuser: Masked Fusion of Joint Multi-Modal Tokenization for End-to-End Autonomous Drivingcited by 3
  12. 2025StereoCarla: A High-Fidelity Driving Dataset for Generalizable Stereocited by 3
18 more
  1. 2025Boosting Zero-shot Stereo Matching using Large-scale Mixed Images Sources in the Real Worldcited by 2
  2. 2026Pixel-Perfect Visual Geometry Estimationcited by 2
  3. 2026Stereo-Inertial Poser: Towards Metric-Accurate Shape-Aware Motion Capture Using Sparse IMUs and a Single Stereo Cameracited by 2
  4. 2024VHS: High-Resolution Iterative Stereo Matching with Visual Hull Priorscited by 1
  5. 2025Iterative Volume Fusion for Asymmetric Stereo Matchingcited by 1
  6. 2025ROVR-Open-Dataset: A Large-Scale Depth Dataset for Autonomous Drivingcited by 1
  7. 2026WideDepth: Millimeter-Accurate Benchmark for Fisheye Depth Estimationcited by 1
  8. 2026Humanoid-OmniOcc: Stereo-Based Full-View Occupancy Dataset for Embodied AIcited by 1
  9. 2026AquaStereo: Enabling Underwater Stereo Matching via Depth-Conditioned Diffusion and Geometry Self-Distillationcited by 1
  10. 2025USAM-Net: A U-Net-based Network for Improved Stereo Correspondence and Scene Depth Estimation using Features from a Pre-trained Image Segmentation networkcited by 0
  11. 2025A Reinforcement Learning Method for Environments with Stochastic Variables: Post-Decision Proximal Policy Optimization with Dual Critic Networkscited by 0
  12. 2025DispBench: Benchmarking Disparity Estimation to Synthetic Corruptionscited by 0
  13. 2025Pixel-Optimization-Free Patch Attack on Stereo Depth Estimationcited by 0
  14. 2025Preserving Guidance in Cost-Volume Retrieval under Extreme LiDAR Sparsity in Iterative Stereocited by 0
  15. 2026StereoFactory: A Unified Merging Framework for Robust Stereo Matchingcited by 0
  16. 2026Lite Any Stereo V2: Faster and Stronger Efficient Zero-Shot Stereo Matchingcited by 0
  17. 2026TrustVLA: Mechanism-Guided Inference-Time Defense Against Vision-Language-Action Backdoorscited by 0
  18. 2026GeoStereo: A Unified Stereo Geometry Estimation Framework for Disparity and Surface Normalcited by 0