mlsanityData to 7 Oct 2026

End-to-End Learning of Geometry and Context for Deep Stereo Regression

arXiv 1703.04309 ↗First posted 13 Mar 2017cs.CV cs.NEcited by 359

Not on the map. Why?

Abstract (arXiv)

We propose a novel deep learning architecture for regressing disparity from a rectified pair of stereo images. We leverage knowledge of the problem's geometry to form a cost volume using deep feature representations. We learn to incorporate contextual information using 3-D convolutions over this volume. Disparity values are regressed from the cost volume using a proposed differentiable soft argmin operation, which allows us to train our method end-to-end to sub-pixel accuracy without any additional post-processing or regularization. We evaluate our method on the Scene Flow and KITTI datasets and on KITTI we set a new state-of-the-art benchmark, while being significantly faster than competing approaches.

Key facts. Cited by 359 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Mar 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 91; 2022: 67; 2023: 51; 2024: 68; 2025: 52; 2026: 30.

359 papers.

Sort:

By area:

  1. 2021RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matchingcited by 348
  2. 2021GMFlow: Learning Optical Flow via Global Matchingcited by 324
  3. 2022Unifying Flow, Stereo and Depth Estimationcited by 270
  4. 2023CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentationcited by 215
  5. 2022Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlationcited by 197
  6. 2021BANMo: Building Animatable 3D Neural Models from Many Casual Videoscited by 195
  7. 2021The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depthcited by 190
  8. 2023Iterative Geometry Encoding Volume for Stereo Matchingcited by 188
  9. 2023AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolationcited by 177
  10. 2025FoundationStereo: Zero-Shot Stereo Matchingcited by 168
  11. 2022CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flowcited by 165
  12. 2021CFNet: Cascade and Fused Cost Volume for Robust Stereo Matchingcited by 153
38 more
  1. 2023DynamicStereo: Consistent Dynamic Depth from Stereo Videoscited by 147
  2. 2024Stop Regressing: Training Value Functions via Classification for Scalable Deep RLcited by 136
  3. 2022Attention Concatenation Volume for Accurate and Efficient Stereo Matchingcited by 130
  4. 2021SMD-Nets: Stereo Mixture Density Networkscited by 118
  5. 2024RaDe-GS: Rasterizing Depth in Gaussian Splattingcited by 110
  6. 2024Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matchingcited by 98
  7. 2024Stereo4D: Learning How Things Move in 3D from Internet Stereo Videoscited by 89
  8. 2023Telling Left from Right: Identifying Geometry-Aware Semantic Correspondencecited by 85
  9. 2022SimpleRecon: 3D Reconstruction Without 3D Convolutionscited by 83
  10. 2021MobileStereoNet: Towards Lightweight Deep Networks for Stereo Matchingcited by 82
  11. 2021Explainability of deep vision-based autonomous driving systems: Review and challengescited by 80
  12. 2021LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detectorcited by 69
  13. 2024GS2Mesh: Surface Reconstruction from Gaussian Splatting via Novel Stereo Viewscited by 65
  14. 2022Multi-Frame Self-Supervised Depth with Transformerscited by 64
  15. 2022Accurate and Efficient Stereo Matching via Attention Concatenation Volumecited by 59
  16. 2021IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereocited by 56
  17. 2024IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo Matchingcited by 55
  18. 2021ARVo: Learning All-Range Volumetric Correspondence for Video Deblurringcited by 54
  19. 2021Learning Optical Flow from a Few Matchescited by 53
  20. 2022CATs++: Boosting Cost Aggregation with Convolutions and Transformerscited by 53
  21. 2022STS: Surround-view Temporal Stereo for Multi-view 3D Detectioncited by 53
  22. 2025DEFOM-Stereo: Depth Foundation Model Based Stereo Matchingcited by 51
  23. 2022MVSFormer: Multi-View Stereo by Learning Robust Image Features and Temperature-based Depthcited by 50
  24. 2022Open Challenges in Deep Stereo: the Booster Datasetcited by 48
  25. 2021Correlate-and-Excite: Real-Time Stereo Matching via Guided Cost Volume Excitationcited by 47
  26. 2021Bilateral Grid Learning for Stereo Matching Networkscited by 46
  27. 2021MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronizationcited by 46
  28. 2022Revisiting Domain Generalized Stereo Matching Networks from a Feature Consistency Perspectivecited by 46
  29. 2023NeRF-Supervised Deep Stereocited by 46
  30. 2024Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Failcited by 45
  31. 2021VolumeFusion: Deep Depth Fusion for 3D Scene Reconstructioncited by 44
  32. 2022GraftNet: Towards Domain Generalized Stereo Matching with a Broad-Spectrum and Task-Oriented Featurecited by 43
  33. 2022DiffuStereo: High Quality Human Reconstruction via Diffusion-based Stereo Using Sparse Camerascited by 43
  34. 2021Extreme Rotation Estimation using Dense Correlation Volumescited by 42
  35. 2021Full Surround Monodepth from Multiple Camerascited by 41
  36. 2022ITSA: An Information-Theoretic Approach to Automatic Shortcut Avoidance and Domain Generalization in Stereo Matching Networkscited by 39
  37. 2021StereoPIFu: Depth Aware Clothed Human Digitization via Stereo Visioncited by 38
  38. 2024Neural Markov Random Field for Stereo Matchingcited by 38

50 most cited of 359 All 359 (JSON)