mlsanityData to 7 Oct 2026

Pyramid Stereo Matching Network

arXiv 1803.08669 ↗First posted 23 Mar 2018cs.CVcited by 486

Not on the map. Why?

Abstract (arXiv)

Recent work has shown that depth estimation from a stereo pair of images can be formulated as a supervised learning task to be resolved with convolutional neural networks (CNNs). However, current architectures rely on patch-based Siamese networks, lacking the means to exploit context information for finding correspondence in illposed regions. To tackle this problem, we propose PSMNet, a pyramid stereo matching network consisting of two main modules: spatial pyramid pooling and 3D CNN. The spatial pyramid pooling module takes advantage of the capacity of global context information by aggregating context in different scales and locations to form a cost volume. The 3D CNN learns to regularize cost volume using stacked multiple hourglass networks in conjunction with intermediate supervision. The proposed approach was evaluated on several benchmark datasets. Our method ranked first in the KITTI 2012 and 2015 leaderboards before March 18, 2018. The codes of PSMNet are available at: https://github.com/JiaRenChang/PSMNet.

Key facts. Cited by 486 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Mar 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 106; 2022: 86; 2023: 70; 2024: 99; 2025: 78; 2026: 47.

486 papers.

Sort:

By area:

  1. 2021RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matchingcited by 348
  2. 2023SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Drivingcited by 310
  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. 2021The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depthcited by 190
  7. 2023Iterative Geometry Encoding Volume for Stereo Matchingcited by 188
  8. 2024Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairscited by 171
  9. 2025FoundationStereo: Zero-Shot Stereo Matchingcited by 168
  10. 2022CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flowcited by 165
  11. 2022CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completioncited by 158
  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. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  3. 2022Attention Concatenation Volume for Accurate and Efficient Stereo Matchingcited by 130
  4. 2021SMD-Nets: Stereo Mixture Density Networkscited by 118
  5. 20213D Object Detection for Autonomous Driving: A Surveycited by 106
  6. 2022P3Depth: Monocular Depth Estimation with a Piecewise Planarity Priorcited by 106
  7. 2024Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matchingcited by 98
  8. 2024Stereo4D: Learning How Things Move in 3D from Internet Stereo Videoscited by 89
  9. 2021Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentationcited by 88
  10. 2021Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detectioncited by 84
  11. 2021P2T: Pyramid Pooling Transformer for Scene Understandingcited by 84
  12. 2022SimpleRecon: 3D Reconstruction Without 3D Convolutionscited by 83
  13. 2021MobileStereoNet: Towards Lightweight Deep Networks for Stereo Matchingcited by 82
  14. 2021Explainability of deep vision-based autonomous driving systems: Review and challengescited by 80
  15. 2022SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimationcited by 76
  16. 2021LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detectorcited by 69
  17. 2022MonoDistill: Learning Spatial Features for Monocular 3D Object Detectioncited by 68
  18. 20223D Object Detection from Images for Autonomous Driving: A Surveycited by 66
  19. 2024GS2Mesh: Surface Reconstruction from Gaussian Splatting via Novel Stereo Viewscited by 65
  20. 2022Multi-Frame Self-Supervised Depth with Transformerscited by 64
  21. 2021Multi-Modal 3D Object Detection in Autonomous Driving: a Surveycited by 63
  22. 2021Unsupervised Depth Completion with Calibrated Backprojection Layerscited by 61
  23. 2022Accurate and Efficient Stereo Matching via Attention Concatenation Volumecited by 59
  24. 2021Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistencycited by 58
  25. 2024IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo Matchingcited by 55
  26. 2022STS: Surround-view Temporal Stereo for Multi-view 3D Detectioncited by 53
  27. 2021Progressive Coordinate Transforms for Monocular 3D Object Detectioncited by 52
  28. 2025DEFOM-Stereo: Depth Foundation Model Based Stereo Matchingcited by 51
  29. 2022Open Challenges in Deep Stereo: the Booster Datasetcited by 48
  30. 2024MoCha-Stereo: Motif Channel Attention Network for Stereo Matchingcited by 48
  31. 2021Correlate-and-Excite: Real-Time Stereo Matching via Guided Cost Volume Excitationcited by 47
  32. 2022Ithaca365: Dataset and Driving Perception under Repeated and Challenging Weather Conditionscited by 47
  33. 2021Bilateral Grid Learning for Stereo Matching Networkscited by 46
  34. 2021Multi-View Depth Estimation by Fusing Single-View Depth Probability with Multi-View Geometrycited by 46
  35. 2022Revisiting Domain Generalized Stereo Matching Networks from a Feature Consistency Perspectivecited by 46
  36. 2023NeRF-Supervised Deep Stereocited by 46
  37. 2024Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Failcited by 45
  38. 2021VolumeFusion: Deep Depth Fusion for 3D Scene Reconstructioncited by 44

50 most cited of 486 All 486 (JSON)