mlsanityData to 7 Oct 2026

RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching

arXiv 2109.07547 ↗First posted 15 Sep 2021cs.CVcited by 348

Not on the map. Why?

Abstract (arXiv)

We introduce RAFT-Stereo, a new deep architecture for rectified stereo based on the optical flow network RAFT. We introduce multi-level convolutional GRUs, which more efficiently propagate information across the image. A modified version of RAFT-Stereo can perform accurate real-time inference. RAFT-stereo ranks first on the Middlebury leaderboard, outperforming the next best method on 1px error by 29% and outperforms all published work on the ETH3D two-view stereo benchmark. Code is available at https://github.com/princeton-vl/RAFT-Stereo.

Key facts. Cited by 348 papers in the map (data through 7 Oct 2026). Builds on 29 of its 49 references that are in the map. First posted on arXiv 15 Sep 2021.

Builds on

29 of 49 references.

References · 29

  1. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  2. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
  3. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,187
  4. 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,054
  5. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 878
  6. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 780
  7. 2020TartanAir: A Dataset to Push the Limits of Visual SLAMcited by 494
  8. 2018Pyramid Stereo Matching Networkcited by 486
  9. 2017End-to-End Learning of Geometry and Context for Deep Stereo Regressioncited by 359
  10. 2019GA-Net: Guided Aggregation Net for End-to-end Stereo Matchingcited by 242
  11. 2019Group-wise Correlation Stereo Networkcited by 235
  12. 2017Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Ratescited by 196
17 more
  1. 2020Hierarchical Neural Architecture Search for Deep Stereo Matchingcited by 166
  2. 2018Learning Depth with Convolutional Spatial Propagation Networkcited by 135
  3. 2019Hierarchical Deep Stereo Matching on High-resolution Imagescited by 126
  4. 2020HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo Matchingcited by 120
  5. 2019Domain-invariant Stereo Matching Networkscited by 108
  6. 2018Hierarchical Discrete Distribution Decomposition for Match Density Estimationcited by 93
  7. 2018Falling Things: A Synthetic Dataset for 3D Object Detection and Pose Estimationcited by 92
  8. 2014Computing the Stereo Matching Cost with a Convolutional Neural Networkcited by 74
  9. 2017Cascade Residual Learning: A Two-stage Convolutional Neural Network for Stereo Matchingcited by 63
  10. 2019Adaptive Unimodal Cost Volume Filtering for Deep Stereo Matchingcited by 55
  11. 2020Learning Stereo from Single Imagescited by 44
  12. 2019EdgeStereo: An Effective Multi-Task Learning Network for Stereo Matching and Edge Detectioncited by 39
  13. 2020Bi3D: Stereo Depth Estimation via Binary Classificationscited by 34
  14. 2020AdaStereo: A Simple and Efficient Approach for Adaptive Stereo Matchingcited by 31
  15. 2021PVStereo: Pyramid Voting Module for End-to-End Self-Supervised Stereo Matchingcited by 28
  16. 2016Continuous 3D Label Stereo Matching using Local Expansion Movescited by 16
  17. 2019AMNet: Deep Atrous Multiscale Stereo Disparity Estimation Networkscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 36; 2023: 46; 2024: 89; 2025: 103; 2026: 69.

348 papers.

Sort:

By area:

  1. 2024Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimationcited by 389
  2. 2023Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Imagecited by 357
  3. 2022Unifying Flow, Stereo and Depth Estimationcited by 270
  4. 2022Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlationcited by 197
  5. 2023Iterative Geometry Encoding Volume for Stereo Matchingcited by 188
  6. 2023AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolationcited by 177
  7. 2023Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereocited by 170
  8. 2023GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesiscited by 170
  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. 2023DynamicStereo: Consistent Dynamic Depth from Stereo Videoscited by 147
  12. 2023Infinite Photorealistic Worlds using Procedural Generationcited by 142
38 more
  1. 2024Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generationcited by 129
  2. 2024Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matchingcited by 98
  3. 2022CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flowcited by 82
  4. 2024GS2Mesh: Surface Reconstruction from Gaussian Splatting via Novel Stereo Viewscited by 65
  5. 2022Accurate and Efficient Stereo Matching via Attention Concatenation Volumecited by 59
  6. 2021IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereocited by 56
  7. 2024IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo Matchingcited by 55
  8. 2023IEBins: Iterative Elastic Bins for Monocular Depth Estimationcited by 53
  9. 2022Multiview Stereo with Cascaded Epipolar RAFTcited by 51
  10. 2024Robot See Robot Do: Imitating Articulated Object Manipulation with Monocular 4D Reconstructioncited by 51
  11. 2025DEFOM-Stereo: Depth Foundation Model Based Stereo Matchingcited by 51
  12. 2022Open Challenges in Deep Stereo: the Booster Datasetcited by 48
  13. 2023LRRU: Long-short Range Recurrent Updating Networks for Depth Completioncited by 48
  14. 2024MoCha-Stereo: Motif Channel Attention Network for Stereo Matchingcited by 48
  15. 2023NeRF-Supervised Deep Stereocited by 46
  16. 2024Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Failcited by 45
  17. 2022GraftNet: Towards Domain Generalized Stereo Matching with a Broad-Spectrum and Task-Oriented Featurecited by 43
  18. 2022DiffuStereo: High Quality Human Reconstruction via Diffusion-based Stereo Using Sparse Camerascited by 43
  19. 2021Toward Practical Monocular Indoor Depth Estimationcited by 42
  20. 2024Neural Markov Random Field for Stereo Matchingcited by 38
  21. 2022Context-Enhanced Stereo Transformercited by 37
  22. 2023Uncertainty Guided Adaptive Warping for Robust and Efficient Stereo Matchingcited by 36
  23. 2023Tracking and Mapping in Medical Computer Vision: A Reviewcited by 36
  24. 2023Learning Depth Estimation for Transparent and Mirror Surfacescited by 34
  25. 2024MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videoscited by 34
  26. 2023Booster: a Benchmark for Depth from Images of Specular and Transparent Surfacescited by 33
  27. 2022Disentangling Architecture and Training for Optical Flowcited by 32
  28. 2023OpenStereo: A Comprehensive Benchmark for Stereo Matching and Strong Baselinecited by 28
  29. 2024LightStereo: Channel Boost Is All You Need for Efficient 2D Cost Aggregationcited by 28
  30. 2023RoadFormer: Duplex Transformer for RGB-Normal Semantic Road Scene Parsingcited by 27
  31. 2024Match-Stereo-Videos: Bidirectional Alignment for Consistent Dynamic Stereo Matchingcited by 24
  32. 2024Playing to Vision Foundation Model's Strengths in Stereo Matchingcited by 23
  33. 2024OGNI-DC: Robust Depth Completion with Optimization-Guided Neural Iterationscited by 23
  34. 2024A Survey on Deep Stereo Matching in the Twentiescited by 23
  35. 2025Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matchingcited by 23
  36. 2024GPS-Gaussian+: Generalizable Pixel-wise 3D Gaussian Splatting for Real-Time Human-Scene Rendering from Sparse Viewscited by 22
  37. 2023Bridging Stereo Geometry and BEV Representation with Reliable Mutual Interaction for Semantic Scene Completioncited by 21
  38. 2022Self-Supervised Depth Estimation in Laparoscopic Image using 3D Geometric Consistencycited by 19

50 most cited of 348 All 348 (JSON)