mlsanityData to 14 Oct 2026

A Survey on Deep Stereo Matching in the Twenties

arXiv 2407.07816 ↗First posted 10 Jul 2024cs.CVcited by 23

Not on the map. Why?

Abstract (arXiv)

Stereo matching is close to hitting a half-century of history, yet witnessed a rapid evolution in the last decade thanks to deep learning. While previous surveys in the late 2010s covered the first stage of this revolution, the last five years of research brought further ground-breaking advancements to the field. This paper aims to fill this gap in a two-fold manner: first, we offer an in-depth examination of the latest developments in deep stereo matching, focusing on the pioneering architectural designs and groundbreaking paradigms that have redefined the field in the 2020s; second, we present a thorough analysis of the critical challenges that have emerged alongside these advances, providing a comprehensive taxonomy of these issues and exploring the state-of-the-art techniques proposed to address them. By reviewing both the architectural innovations and the key challenges, we offer a holistic view of deep stereo matching and highlight the specific areas that require further investigation. To accompany this survey, we maintain a regularly updated project page that catalogs papers on deep stereo matching in our Awesome-Deep-Stereo-Matching (https://github.com/fabiotosi92/Awesome-Deep-Stereo-Matching) repository.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). Builds on 134 of its 210 references that are in the map. First posted on arXiv 10 Jul 2024.

Builds on

134 of 210 references.

References · 134

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  5. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  6. 2017CARLA: An Open Urban Driving Simulatorcited by 2,449
  7. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
  8. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
  9. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
  10. 2024Depth Anything V2cited by 1,422
  11. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,360
  12. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,299
38 more
  1. 2019Event-based Vision: A Surveycited by 1,016
  2. 2024Grounding Image Matching in 3D with MASt3Rcited by 983
  3. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 881
  4. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 820
  5. 2020TartanAir: A Dataset to Push the Limits of Visual SLAMcited by 506
  6. 2018Pyramid Stereo Matching Networkcited by 489
  7. 2019Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matchingcited by 417
  8. 2017End-to-End Learning of Geometry and Context for Deep Stereo Regressioncited by 360
  9. 2020Virtual KITTI 2cited by 353
  10. 2021RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matchingcited by 353
  11. 2019High Speed and High Dynamic Range Video with an Event Cameracited by 345
  12. 2016Virtual Worlds as Proxy for Multi-Object Tracking Analysiscited by 341
  13. 2021DSEC: A Stereo Event Camera Dataset for Driving Scenarioscited by 303
  14. 2022Unifying Flow, Stereo and Depth Estimationcited by 275
  15. 2018The Multi Vehicle Stereo Event Camera Dataset: An Event Camera Dataset for 3D Perceptioncited by 254
  16. 2019GA-Net: Guided Aggregation Net for End-to-end Stereo Matchingcited by 244
  17. 2019Group-wise Correlation Stereo Networkcited by 235
  18. 2020AANet: Adaptive Aggregation Network for Efficient Stereo Matchingcited by 202
  19. 2022Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlationcited by 197
  20. 2020Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective with Transformerscited by 190
  21. 2023Iterative Geometry Encoding Volume for Stereo Matchingcited by 190
  22. 2019Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Drivingcited by 188
  23. 2023Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereocited by 172
  24. 2020Hierarchical Neural Architecture Search for Deep Stereo Matchingcited by 166
  25. 2022CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flowcited by 166
  26. 2021CFNet: Cascade and Fused Cost Volume for Robust Stereo Matchingcited by 154
  27. 2015Stereo Matching by Training a Convolutional Neural Network to Compare Image Patchescited by 151
  28. 2023DynamicStereo: Consistent Dynamic Depth from Stereo Videoscited by 148
  29. 2018Learning Depth with Convolutional Spatial Propagation Networkcited by 136
  30. 2022Attention Concatenation Volume for Accurate and Efficient Stereo Matchingcited by 130
  31. 2019Hierarchical Deep Stereo Matching on High-resolution Imagescited by 126
  32. 2020RAFT-3D: Scene Flow using Rigid-Motion Embeddingscited by 122
  33. 2020HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo Matchingcited by 120
  34. 2021SMD-Nets: Stereo Mixture Density Networkscited by 120
  35. 2019DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatchcited by 114
  36. 2019Domain-invariant Stereo Matching Networkscited by 109
  37. 2024Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matchingcited by 99
  38. 2018Hierarchical Discrete Distribution Decomposition for Match Density Estimationcited by 93

50 most cited of 134 All 134 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 4; 2025: 12; 2026: 7.

23 papers.

Sort:

By area:

  1. 2025DEFOM-Stereo: Depth Foundation Model Based Stereo Matchingcited by 52
  2. 2024Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Failcited by 47
  3. 2025Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matchingcited by 28
  4. 2024Self-Evolving Depth-Supervised 3D Gaussian Splatting from Rendered Stereo Pairscited by 11
  5. 2025Towards Open-World Generation of Stereo Images and Unsupervised Matchingcited by 6
  6. 2024Stereo Anything: Unifying Zero-shot Stereo Matching with Large-Scale Mixed Datacited by 5
  7. 2025DERD-Net: Learning Depth from Event-based Ray Densitiescited by 4
  8. 2025NTIRE 2025 Challenge on HR Depth from Images of Specular and Transparent Surfacescited by 3
  9. 2025Boosting Omnidirectional Stereo Matching with a Pre-trained Depth Foundation Modelcited by 1
  10. 2025SpikeStereoNet: A Brain-Inspired Framework for Stereo Depth Estimation from Spike Streamscited by 1
  11. 2025CogStereo: Neural Stereo Matching with Implicit Spatial Cognition Embeddingcited by 1
  12. 2025Robust Shape from Focus via Multiscale Directional Dilated Laplacian and Recurrent Networkcited by 1
11 more
  1. 2026WideDepth: Millimeter-Accurate Benchmark for Fisheye Depth Estimationcited by 1
  2. 2024Pseudo-Stereo Inputs: A Solution to the Occlusion Challenge in Self-Supervised Stereo Matchingcited by 0
  3. 2025SteROI-D: System Design and Mapping for Stereo Depth Inference on Regions of Interestcited by 0
  4. 2025DepthVanish: Optimizing Adversarial Interval Structures for Stereo-Depth-Invisible Patchescited by 0
  5. 2025PPMStereo: Pick-and-Play Memory Construction for Consistent Dynamic Stereo Matchingcited by 0
  6. 2026Learning Vision-Based Omnidirectional Navigation: A Teacher-Student Approach Using Monocular Depth Estimationcited by 0
  7. 2026EventHub: Data Factory for Generalizable Event-Based Stereo Networks without Active Sensorscited by 0
  8. 2026Bidirectional Cross-Modal Prompting for Event-Frame Asymmetric Stereocited by 0
  9. 2026Depth-Semantic Alignment and Affinity-Guided Fusion for Structured Radar Point Cloud Generationcited by 0
  10. 2026STEREOFLOW: Progressive Stereo Matching with StereoDiT and Transition Flow Matchingcited by 0
  11. 2026SeasonStereo: Robust Dense Stereo Matching for Multi-Date Satellite Imagery via Generative AIcited by 0