mlsanityData to 13 Oct 2026

Domain-invariant Stereo Matching Networks

arXiv 1911.13287 ↗First posted 29 Nov 2019cs.CVcited by 108

Not on the map. Why?

Abstract (arXiv)

State-of-the-art stereo matching networks have difficulties in generalizing to new unseen environments due to significant domain differences, such as color, illumination, contrast, and texture. In this paper, we aim at designing a domain-invariant stereo matching network (DSMNet) that generalizes well to unseen scenes. To achieve this goal, we propose i) a novel "domain normalization" approach that regularizes the distribution of learned representations to allow them to be invariant to domain differences, and ii) a trainable non-local graph-based filter for extracting robust structural and geometric representations that can further enhance domain-invariant generalizations. When trained on synthetic data and generalized to real test sets, our model performs significantly better than all state-of-the-art models. It even outperforms some deep learning models (e.g. MC-CNN) fine-tuned with test-domain data.

Key facts. Cited by 108 papers in the map (data through 13 Oct 2026). First posted on arXiv 29 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 17; 2022: 15; 2023: 17; 2024: 28; 2025: 20; 2026: 11.

108 papers.

Sort:

By area:

  1. 2021RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matchingcited by 352
  2. 2021The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depthcited by 190
  3. 2023Iterative Geometry Encoding Volume for Stereo Matchingcited by 189
  4. 2025FoundationStereo: Zero-Shot Stereo Matchingcited by 170
  5. 2021CFNet: Cascade and Fused Cost Volume for Robust Stereo Matchingcited by 154
  6. 2023DynamicStereo: Consistent Dynamic Depth from Stereo Videoscited by 148
  7. 2021AutoFlow: Learning a Better Training Set for Optical Flowcited by 102
  8. 2022SimpleRecon: 3D Reconstruction Without 3D Convolutionscited by 83
  9. 2024IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo Matchingcited by 58
  10. 2025DEFOM-Stereo: Depth Foundation Model Based Stereo Matchingcited by 52
  11. 2022Open Challenges in Deep Stereo: the Booster Datasetcited by 48
  12. 2024MoCha-Stereo: Motif Channel Attention Network for Stereo Matchingcited by 48
38 more
  1. 2021Bilateral Grid Learning for Stereo Matching Networkscited by 46
  2. 2022Revisiting Domain Generalized Stereo Matching Networks from a Feature Consistency Perspectivecited by 46
  3. 2023NeRF-Supervised Deep Stereocited by 46
  4. 2024Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Failcited by 46
  5. 2021Self-supervised Monocular Depth Estimation for All Day Images using Domain Separationcited by 44
  6. 2022GraftNet: Towards Domain Generalized Stereo Matching with a Broad-Spectrum and Task-Oriented Featurecited by 43
  7. 2022DiffuStereo: High Quality Human Reconstruction via Diffusion-based Stereo Using Sparse Camerascited by 43
  8. 2022DIP: Deep Inverse Patchmatch for High-Resolution Optical Flowcited by 40
  9. 2021Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AIcited by 39
  10. 2021TANDEM: Tracking and Dense Mapping in Real-time using Deep Multi-view Stereocited by 39
  11. 2022ITSA: An Information-Theoretic Approach to Automatic Shortcut Avoidance and Domain Generalization in Stereo Matching Networkscited by 39
  12. 2024Neural Markov Random Field for Stereo Matchingcited by 38
  13. 2023Uncertainty Guided Adaptive Warping for Robust and Efficient Stereo Matchingcited by 36
  14. 2023Booster: a Benchmark for Depth from Images of Specular and Transparent Surfacescited by 33
  15. 2021Local Similarity Pattern and Cost Self-Reassembling for Deep Stereo Matching Networkscited by 32
  16. 2023TMA: Temporal Motion Aggregation for Event-based Optical Flowcited by 32
  17. 2023OpenStereo: A Comprehensive Benchmark for Stereo Matching and Strong Baselinecited by 30
  18. 2021Learning optical flow from still imagescited by 28
  19. 2024LightStereo: Channel Boost Is All You Need for Efficient 2D Cost Aggregationcited by 28
  20. 2025MVSAnywhere: Zero-Shot Multi-View Stereocited by 26
  21. 2025Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matchingcited by 26
  22. 2024A Survey on Deep Stereo Matching in the Twentiescited by 23
  23. 2023Digging Into Uncertainty-based Pseudo-label for Robust Stereo Matchingcited by 22
  24. 2021Neural Disparity Refinement for Arbitrary Resolution Stereocited by 20
  25. 2023Adaptive Multi-Modal Cross-Entropy Loss for Stereo Matchingcited by 19
  26. 2023MACARONS: Mapping And Coverage Anticipation with RGB Online Self-Supervisioncited by 18
  27. 2023Revisiting Depth Completion from a Stereo Matching Perspective for Cross-domain Generalizationcited by 18
  28. 2023CGI-Stereo: Accurate and Real-Time Stereo Matching via Context and Geometry Interactioncited by 17
  29. 2023DiffuVolume: Diffusion Model for Volume based Stereo Matchingcited by 16
  30. 2024Robust Synthetic-to-Real Transfer for Stereo Matchingcited by 15
  31. 2025BridgeDepth: Bridging Monocular and Stereo Reasoning with Latent Alignmentcited by 15
  32. 2025Learning Robust Stereo Matching in the Wild with Selective Mixture-of-Expertscited by 13
  33. 2024Federated Online Adaptation for Deep Stereocited by 12
  34. 2024Learning Intra-view and Cross-view Geometric Knowledge for Stereo Matchingcited by 11
  35. 2025Diving into the Fusion of Monocular Priors for Generalized Stereo Matchingcited by 10
  36. 2021M4Depth: Monocular depth estimation for autonomous vehicles in unseen environmentscited by 9
  37. 2024DoubleTake: Geometry Guided Depth Estimationcited by 9
  38. 2025StereoAdapter: Adapting Stereo Depth Estimation to Underwater Scenescited by 9

50 most cited of 108 All 108 (JSON)