mlsanityData to 14 Oct 2026

GA-Net: Guided Aggregation Net for End-to-end Stereo Matching

arXiv 1904.06587 ↗First posted 13 Apr 2019cs.CVcited by 244

Not on the map. Why?

Abstract (arXiv)

In the stereo matching task, matching cost aggregation is crucial in both traditional methods and deep neural network models in order to accurately estimate disparities. We propose two novel neural net layers, aimed at capturing local and the whole-image cost dependencies respectively. The first is a semi-global aggregation layer which is a differentiable approximation of the semi-global matching, the second is the local guided aggregation layer which follows a traditional cost filtering strategy to refine thin structures. These two layers can be used to replace the widely used 3D convolutional layer which is computationally costly and memory-consuming as it has cubic computational/memory complexity. In the experiments, we show that nets with a two-layer guided aggregation block easily outperform the state-of-the-art GC-Net which has nineteen 3D convolutional layers. We also train a deep guided aggregation network (GA-Net) which gets better accuracies than state-of-the-art methods on both Scene Flow dataset and KITTI benchmarks.

Key facts. Cited by 244 papers in the map (data through 14 Oct 2026). First posted on arXiv 13 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 51; 2022: 48; 2023: 36; 2024: 51; 2025: 41; 2026: 17.

244 papers.

Sort:

By area:

  1. 2021RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matchingcited by 353
  2. 2022Unifying Flow, Stereo and Depth Estimationcited by 275
  3. 2022Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlationcited by 197
  4. 2021The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depthcited by 190
  5. 2023Iterative Geometry Encoding Volume for Stereo Matchingcited by 190
  6. 2024Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairscited by 178
  7. 2025FoundationStereo: Zero-Shot Stereo Matchingcited by 173
  8. 2023Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereocited by 172
  9. 2021CFNet: Cascade and Fused Cost Volume for Robust Stereo Matchingcited by 154
  10. 2023DynamicStereo: Consistent Dynamic Depth from Stereo Videoscited by 148
  11. 2022Attention Concatenation Volume for Accurate and Efficient Stereo Matchingcited by 130
  12. 2022QuadTree Attention for Vision Transformerscited by 129
38 more
  1. 2021SMD-Nets: Stereo Mixture Density Networkscited by 120
  2. 2024Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matchingcited by 99
  3. 2024Stereo4D: Learning How Things Move in 3D from Internet Stereo Videoscited by 89
  4. 2022SimpleRecon: 3D Reconstruction Without 3D Convolutionscited by 83
  5. 2021MobileStereoNet: Towards Lightweight Deep Networks for Stereo Matchingcited by 82
  6. 2021LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detectorcited by 70
  7. 2024GS2Mesh: Surface Reconstruction from Gaussian Splatting via Novel Stereo Viewscited by 67
  8. 2022Accurate and Efficient Stereo Matching via Attention Concatenation Volumecited by 59
  9. 2024IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo Matchingcited by 59
  10. 2021CamLiFlow: Bidirectional Camera-LiDAR Fusion for Joint Optical Flow and Scene Flow Estimationcited by 56
  11. 2022STS: Surround-view Temporal Stereo for Multi-view 3D Detectioncited by 53
  12. 2022Hierarchical Normalization for Robust Monocular Depth Estimationcited by 52
  13. 2025DEFOM-Stereo: Depth Foundation Model Based Stereo Matchingcited by 52
  14. 2022Open Challenges in Deep Stereo: the Booster Datasetcited by 48
  15. 2024MoCha-Stereo: Motif Channel Attention Network for Stereo Matchingcited by 48
  16. 2021Correlate-and-Excite: Real-Time Stereo Matching via Guided Cost Volume Excitationcited by 47
  17. 2024Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Failcited by 47
  18. 2021Bilateral Grid Learning for Stereo Matching Networkscited by 46
  19. 2021Learning to Segment Rigid Motions from Two Framescited by 46
  20. 2022Revisiting Domain Generalized Stereo Matching Networks from a Feature Consistency Perspectivecited by 46
  21. 2023NeRF-Supervised Deep Stereocited by 46
  22. 2021There is More than Meets the Eye: Self-Supervised Multi-Object Detection and Tracking with Sound by Distilling Multimodal Knowledgecited by 44
  23. 2021VolumeFusion: Deep Depth Fusion for 3D Scene Reconstructioncited by 44
  24. 2022GraftNet: Towards Domain Generalized Stereo Matching with a Broad-Spectrum and Task-Oriented Featurecited by 43
  25. 2022DiffuStereo: High Quality Human Reconstruction via Diffusion-based Stereo Using Sparse Camerascited by 43
  26. 2022DIP: Deep Inverse Patchmatch for High-Resolution Optical Flowcited by 40
  27. 2024Neural Markov Random Field for Stereo Matchingcited by 40
  28. 2022ITSA: An Information-Theoretic Approach to Automatic Shortcut Avoidance and Domain Generalization in Stereo Matching Networkscited by 39
  29. 2021StereoPIFu: Depth Aware Clothed Human Digitization via Stereo Visioncited by 38
  30. 2022Context-Enhanced Stereo Transformercited by 37
  31. 2022TiG-BEV: Multi-view BEV 3D Object Detection via Target Inner-Geometry Learningcited by 37
  32. 2023Uncertainty Guided Adaptive Warping for Robust and Efficient Stereo Matchingcited by 37
  33. 2023Tracking and Mapping in Medical Computer Vision: A Reviewcited by 36
  34. 2023Learning Depth Estimation for Transparent and Mirror Surfacescited by 34
  35. 2023Booster: a Benchmark for Depth from Images of Specular and Transparent Surfacescited by 33
  36. 2021Local Similarity Pattern and Cost Self-Reassembling for Deep Stereo Matching Networkscited by 32
  37. 2023TMA: Temporal Motion Aggregation for Event-based Optical Flowcited by 32
  38. 2021Input-level Inductive Biases for 3D Reconstructioncited by 31

50 most cited of 244 All 244 (JSON)