mlsanityData to 14 Oct 2026

Context-Enhanced Stereo Transformer

arXiv 2210.11719 ↗First posted 21 Oct 2022cs.CV cs.AIcited by 37

Not on the map. Why?

Abstract (arXiv)

Stereo depth estimation is of great interest for computer vision research. However, existing methods struggles to generalize and predict reliably in hazardous regions, such as large uniform regions. To overcome these limitations, we propose Context Enhanced Path (CEP). CEP improves the generalization and robustness against common failure cases in existing solutions by capturing the long-range global information. We construct our stereo depth estimation model, Context Enhanced Stereo Transformer (CSTR), by plugging CEP into the state-of-the-art stereo depth estimation method Stereo Transformer. CSTR is examined on distinct public datasets, such as Scene Flow, Middlebury-2014, KITTI-2015, and MPI-Sintel. We find CSTR outperforms prior approaches by a large margin. For example, in the zero-shot synthetic-to-real setting, CSTR outperforms the best competing approaches on Middlebury-2014 dataset by 11%. Our extensive experiments demonstrate that the long-range information is critical for stereo matching task and CEP successfully captures such information.

Key facts. Cited by 37 papers in the map (data through 14 Oct 2026). Builds on 27 of its 38 references that are in the map. First posted on arXiv 21 Oct 2022.

Builds on

27 of 38 references.

References · 27

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2016Densely Connected Convolutional Networkscited by 6,720
  5. 2015Fast R-CNNcited by 2,933
  6. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,316
  7. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,181
  8. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 881
  9. 2018Pyramid Stereo Matching Networkcited by 489
  10. 2021RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matchingcited by 353
  11. 2020Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentationcited by 326
  12. 2021Focal Self-attention for Local-Global Interactions in Vision Transformerscited by 288
15 more
  1. 2018DeepMVS: Learning Multi-view Stereopsiscited by 277
  2. 2019GA-Net: Guided Aggregation Net for End-to-end Stereo Matchingcited by 244
  3. 2019Group-wise Correlation Stereo Networkcited by 235
  4. 2021Attention Mechanisms in Computer Vision: A Surveycited by 232
  5. 2020AANet: Adaptive Aggregation Network for Efficient Stereo Matchingcited by 202
  6. 2020Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective with Transformerscited by 190
  7. 2019An Attentive Survey of Attention Modelscited by 124
  8. 2020A Survey on Deep Learning Techniques for Stereo-based Depth Estimationcited by 90
  9. 2020Monocular Depth Estimation Based On Deep Learning: An Overviewcited by 68
  10. 2020Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimationcited by 43
  11. 2021Temporally Consistent Online Depth Estimation in Dynamic Scenescited by 26
  12. 2021A Decomposition Model for Stereo Matchingcited by 25
  13. 2017Learned Multi-Patch Similaritycited by 24
  14. 2020Extremely Dense Point Correspondences using a Learned Feature Descriptorcited by 20
  15. 2021On the Sins of Image Synthesis Loss for Self-supervised Depth Estimationcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 4; 2024: 11; 2025: 13; 2026: 8.

37 papers.

Sort:

By area:

  1. 2022Unifying Flow, Stereo and Depth Estimationcited by 275
  2. 2025FoundationStereo: Zero-Shot Stereo Matchingcited by 173
  3. 2024IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo Matchingcited by 59
  4. 2024Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Failcited by 47
  5. 2023NeRF-Supervised Deep Stereocited by 46
  6. 2023Learning Depth Estimation for Transparent and Mirror Surfacescited by 34
  7. 2024Improving Gloss-free Sign Language Translation by Reducing Representation Densitycited by 31
  8. 2023ELFNet: Evidential Local-global Fusion for Stereo Matchingcited by 25
  9. 2024Playing to Vision Foundation Model's Strengths in Stereo Matchingcited by 23
  10. 2024A Survey on Deep Stereo Matching in the Twentiescited by 23
  11. 2025BridgeDepth: Bridging Monocular and Stereo Reasoning with Latent Alignmentcited by 15
  12. 2025Learning Robust Stereo Matching in the Wild with Selective Mixture-of-Expertscited by 14
25 more
  1. 2024Federated Online Adaptation for Deep Stereocited by 12
  2. 2024Learning Intra-view and Cross-view Geometric Knowledge for Stereo Matchingcited by 11
  3. 2025Diving into the Fusion of Monocular Priors for Generalized Stereo Matchingcited by 10
  4. 2023Active Stereo Without Pattern Projectorcited by 8
  5. 2025Stereo Any Video: Temporally Consistent Stereo Matchingcited by 8
  6. 2024LiDAR-Event Stereo Fusion with Hallucinationscited by 7
  7. 2024Rethinking Iterative Stereo Matching from Diffusion Bridge Model Perspectivecited by 4
  8. 2025Lite Any Stereo: Efficient Zero-Shot Stereo Matchingcited by 4
  9. 2026Spatial Memory for Out-of-Vision Manipulation in Vision-Language-Actioncited by 4
  10. 2024Depth-aware Volume Attention for Texture-less Stereo Matchingcited by 3
  11. 20253D Visual Illusion Depth Estimationcited by 3
  12. 2025NTIRE 2025 Challenge on HR Depth from Images of Specular and Transparent Surfacescited by 3
  13. 2025Hadamard Attention Recurrent Transformer: A Strong Baseline for Stereo Matching Transformercited by 2
  14. 2025Towards Depth Foundation Model: Recent Trends in Vision-Based Depth Estimationcited by 2
  15. 2024Active Stereo in the Wild through Virtual Pattern Projectioncited by 0
  16. 2025DepthVanish: Optimizing Adversarial Interval Structures for Stereo-Depth-Invisible Patchescited by 0
  17. 2025Preserving Guidance in Cost-Volume Retrieval under Extreme LiDAR Sparsity in Iterative Stereocited by 0
  18. 2025CCNeXt: An Effective Self-Supervised Stereo Depth Estimation Approachcited by 0
  19. 2026StereoAdapter-2: Globally Structure-Consistent Underwater Stereo Depth Estimationcited by 0
  20. 2026EventHub: Data Factory for Generalizable Event-Based Stereo Networks without Active Sensorscited by 0
  21. 2026Bidirectional Cross-Modal Prompting for Event-Frame Asymmetric Stereocited by 0
  22. 2026MLG-Stereo: ViT Based Stereo Matching with Multi-Stage Local-Global Enhancementcited by 0
  23. 2026Lite Any Stereo V2: Faster and Stronger Efficient Zero-Shot Stereo Matchingcited by 0
  24. 2026STEREOFLOW: Progressive Stereo Matching with StereoDiT and Transition Flow Matchingcited by 0
  25. 2026NBS: No Bias Stereocited by 0