mlsanityData to 7 Oct 2026

Computing the Stereo Matching Cost with a Convolutional Neural Network

arXiv 1409.4326 ↗First posted 15 Sep 2014cs.CV cs.LG cs.NEcited by 74

Not on the map. Why?

Abstract (arXiv)

We present a method for extracting depth information from a rectified image pair. We train a convolutional neural network to predict how well two image patches match and use it to compute the stereo matching cost. The cost is refined by cross-based cost aggregation and semiglobal matching, followed by a left-right consistency check to eliminate errors in the occluded regions. Our stereo method achieves an error rate of 2.61 % on the KITTI stereo dataset and is currently (August 2014) the top performing method on this dataset.

Key facts. Cited by 74 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Sep 2014.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 22; 2022: 14; 2023: 7; 2024: 16; 2025: 7; 2026: 8.

74 papers.

Sort:

By area:

  1. 2021RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matchingcited by 348
  2. 2022Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlationcited by 197
  3. 2024Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairscited by 171
  4. 2023DynamicStereo: Consistent Dynamic Depth from Stereo Videoscited by 147
  5. 2022Attention Concatenation Volume for Accurate and Efficient Stereo Matchingcited by 130
  6. 2024RaDe-GS: Rasterizing Depth in Gaussian Splattingcited by 110
  7. 2022Multiview Stereo with Cascaded Epipolar RAFTcited by 51
  8. 2024MoCha-Stereo: Motif Channel Attention Network for Stereo Matchingcited by 48
  9. 2021Bilateral Grid Learning for Stereo Matching Networkscited by 46
  10. 2022Revisiting Domain Generalized Stereo Matching Networks from a Feature Consistency Perspectivecited by 46
  11. 2021DIML/CVL RGB-D Dataset: 2M RGB-D Images of Natural Indoor and Outdoor Scenescited by 45
  12. 2021Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlookcited by 45
38 more
  1. 2024Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Failcited by 45
  2. 2021MVS2D: Efficient Multi-view Stereo via Attention-Driven 2D Convolutionscited by 43
  3. 2022GraftNet: Towards Domain Generalized Stereo Matching with a Broad-Spectrum and Task-Oriented Featurecited by 43
  4. 2022DiffuStereo: High Quality Human Reconstruction via Diffusion-based Stereo Using Sparse Camerascited by 43
  5. 2023Uncertainty Guided Adaptive Warping for Robust and Efficient Stereo Matchingcited by 36
  6. 2023Building Rearticulable Models for Arbitrary 3D Objects from 4D Point Cloudscited by 34
  7. 2021Local Similarity Pattern and Cost Self-Reassembling for Deep Stereo Matching Networkscited by 32
  8. 2024Adaptive Fusion of Single-View and Multi-View Depth for Autonomous Drivingcited by 30
  9. 2025MVSAnywhere: Zero-Shot Multi-View Stereocited by 26
  10. 2021A Decomposition Model for Stereo Matchingcited by 25
  11. 2022Trust, but Verify: Cross-Modality Fusion for HD Map Change Detectioncited by 25
  12. 2024Match-Stereo-Videos: Bidirectional Alignment for Consistent Dynamic Stereo Matchingcited by 24
  13. 2025MonSter++: Unified Stereo Matching, Multi-view Stereo, and Real-time Stereo with Monodepth Priorscited by 19
  14. 2021SimNet: Enabling Robust Unknown Object Manipulation from Pure Synthetic Data via Stereocited by 18
  15. 2024All-in-One: Transferring Vision Foundation Models into Stereo Matchingcited by 16
  16. 2024Robust Synthetic-to-Real Transfer for Stereo Matchingcited by 15
  17. 2021Deep Multi-View Stereo gone wildcited by 11
  18. 2022A Survey on RGB-D Datasetscited by 11
  19. 2024Match Stereo Videos via Bidirectional Alignmentcited by 11
  20. 2021Dr-Vectors: Decision Residual Networks and an Improved Loss for Speaker Recognitioncited by 10
  21. 2023Intrinsic Self-Supervision for Data Quality Auditscited by 8
  22. 2021ActiveZero: Mixed Domain Learning for Active Stereovision with Zero Annotationcited by 7
  23. 2021AdaStereo: An Efficient Domain-Adaptive Stereo Matching Approachcited by 7
  24. 2021Semi-synthesis: A fast way to produce effective datasets for stereo matchingcited by 6
  25. 2024Stereo Risk: A Continuous Modeling Approach to Stereo Matchingcited by 6
  26. 2022A Comparative Study on Deep-Learning Methods for Dense Image Matching of Multi-angle and Multi-date Remote Sensing Stereo Imagescited by 5
  27. 2022Self-Supervised Intensity-Event Stereo Matchingcited by 5
  28. 2024Extending 6D Object Pose Estimators for Stereo Visioncited by 5
  29. 2021Monocular Road Planar Parallax Estimationcited by 4
  30. 2022Depth Estimation by Combining Binocular Stereo and Monocular Structured-Lightcited by 4
  31. 2025Consistency-aware Self-Training for Iterative-based Stereo Matchingcited by 4
  32. 2024DCVSMNet: Double Cost Volume Stereo Matching Networkcited by 3
  33. 2021Learning Efficient Photometric Feature Transform for Multi-view Stereocited by 2
  34. 2023TransTouch: Learning Transparent Objects Depth Sensing Through Sparse Touchescited by 2
  35. 2024Left-right Discrepancy for Adversarial Attack on Stereo Networkscited by 2
  36. 2024Reusable Architecture Growth for Continual Stereo Matchingcited by 2
  37. 2025PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Modelscited by 2
  38. 2026WAFT-Stereo: Warping-Alone Field Transforms for Stereo Matchingcited by 2

50 most cited of 74 All 74 (JSON)