mlsanityData to 7 Oct 2026

Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective with Transformers

arXiv 2011.02910 ↗First posted 5 Nov 2020cs.CVcited by 190

Not on the map. Why?

Abstract (arXiv)

Stereo depth estimation relies on optimal correspondence matching between pixels on epipolar lines in the left and right images to infer depth. In this work, we revisit the problem from a sequence-to-sequence correspondence perspective to replace cost volume construction with dense pixel matching using position information and attention. This approach, named STereo TRansformer (STTR), has several advantages: It 1) relaxes the limitation of a fixed disparity range, 2) identifies occluded regions and provides confidence estimates, and 3) imposes uniqueness constraints during the matching process. We report promising results on both synthetic and real-world datasets and demonstrate that STTR generalizes across different domains, even without fine-tuning.

Key facts. Cited by 190 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 15; 2022: 39; 2023: 36; 2024: 50; 2025: 36; 2026: 14.

190 papers.

Sort:

By area:

  1. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 974
  2. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 568
  3. 2021GMFlow: Learning Optical Flow via Global Matchingcited by 324
  4. 2022Unifying Flow, Stereo and Depth Estimationcited by 270
  5. 2022Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlationcited by 197
  6. 2023Iterative Geometry Encoding Volume for Stereo Matchingcited by 188
  7. 2025FoundationStereo: Zero-Shot Stereo Matchingcited by 168
  8. 2021SPViT: Enabling Faster Vision Transformers via Soft Token Pruningcited by 165
  9. 2023DynamicStereo: Consistent Dynamic Depth from Stereo Videoscited by 147
  10. 2022QuadTree Attention for Vision Transformerscited by 129
  11. 2022Neural Rendering for Stereo 3D Reconstruction of Deformable Tissues in Robotic Surgerycited by 122
  12. 2021TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformerscited by 117
38 more
  1. 2023CompletionFormer: Depth Completion with Convolutions and Vision Transformerscited by 92
  2. 2023Hierarchical Dense Correlation Distillation for Few-Shot Segmentationcited by 84
  3. 2022SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimationcited by 76
  4. 2023EndoSurf: Neural Surface Reconstruction of Deformable Tissues with Stereo Endoscope Videoscited by 68
  5. 2022Multi-Frame Self-Supervised Depth with Transformerscited by 64
  6. 2024IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo Matchingcited by 55
  7. 2025DEFOM-Stereo: Depth Foundation Model Based Stereo Matchingcited by 51
  8. 2022MVSTER: Epipolar Transformer for Efficient Multi-View Stereocited by 50
  9. 2024MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereocited by 49
  10. 2022MulT: An End-to-End Multitask Learning Transformercited by 47
  11. 2021E-DSSR: Efficient Dynamic Surgical Scene Reconstruction with Transformer-based Stereoscopic Depth Perceptioncited by 46
  12. 2022Revisiting Domain Generalized Stereo Matching Networks from a Feature Consistency Perspectivecited by 46
  13. 2023NeRF-Supervised Deep Stereocited by 46
  14. 2024Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Failcited by 45
  15. 2023Neural LerPlane Representations for Fast 4D Reconstruction of Deformable Tissuescited by 44
  16. 2022GraftNet: Towards Domain Generalized Stereo Matching with a Broad-Spectrum and Task-Oriented Featurecited by 43
  17. 2024Endo-4DGS: Endoscopic Monocular Scene Reconstruction with 4D Gaussian Splattingcited by 43
  18. 2021Boundary-aware Transformers for Skin Lesion Segmentationcited by 39
  19. 2024Neural Markov Random Field for Stereo Matchingcited by 38
  20. 2022Context-Enhanced Stereo Transformercited by 37
  21. 2023Improving Depth Gradient Continuity in Transformers: A Comparative Study on Monocular Depth Estimation with CNNcited by 35
  22. 2023Learning Depth Estimation for Transparent and Mirror Surfacescited by 34
  23. 2024EndoGS: Deformable Endoscopic Tissues Reconstruction with Gaussian Splattingcited by 33
  24. 2021Input-level Inductive Biases for 3D Reconstructioncited by 31
  25. 2022MeshMAE: Masked Autoencoders for 3D Mesh Data Analysiscited by 31
  26. 2023OpenStereo: A Comprehensive Benchmark for Stereo Matching and Strong Baselinecited by 28
  27. 2023CosPGD: an efficient white-box adversarial attack for pixel-wise prediction taskscited by 27
  28. 2021Temporally Consistent Online Depth Estimation in Dynamic Scenescited by 26
  29. 2023ELFNet: Evidential Local-global Fusion for Stereo Matchingcited by 25
  30. 2022RFormer: Transformer-based Generative Adversarial Network for Real Fundus Image Restoration on A New Clinical Benchmarkcited by 24
  31. 2024A Survey on Deep Stereo Matching in the Twentiescited by 23
  32. 2024UFORecon: Generalizable Sparse-View Surface Reconstruction from Arbitrary and UnFavOrable Setscited by 22
  33. 2022WT-MVSNet: Window-based Transformers for Multi-view Stereocited by 20
  34. 2024EndoGaussian: Real-time Gaussian Splatting for Dynamic Endoscopic Scene Reconstructioncited by 20
  35. 2022Transformers in Self-Supervised Monocular Depth Estimation with Unknown Camera Intrinsicscited by 19
  36. 2023Global Occlusion-Aware Transformer for Robust Stereo Matchingcited by 19
  37. 2024SVG: 3D Stereoscopic Video Generation via Denoising Frame Matrixcited by 19
  38. 2022Depth Field Networks for Generalizable Multi-view Scene Representationcited by 17

50 most cited of 190 All 190 (JSON)