mlsanityData to 7 Oct 2026

A Decomposition Model for Stereo Matching

arXiv 2104.07516 ↗First posted 15 Apr 2021cs.CVcited by 25

Not on the map. Why?

Abstract (arXiv)

In this paper, we present a decomposition model for stereo matching to solve the problem of excessive growth in computational cost (time and memory cost) as the resolution increases. In order to reduce the huge cost of stereo matching at the original resolution, our model only runs dense matching at a very low resolution and uses sparse matching at different higher resolutions to recover the disparity of lost details scale-by-scale. After the decomposition of stereo matching, our model iteratively fuses the sparse and dense disparity maps from adjacent scales with an occlusion-aware mask. A refinement network is also applied to improving the fusion result. Compared with high-performance methods like PSMNet and GANet, our method achieves 10-100× speed increase while obtaining comparable disparity estimation results.

Key facts. Cited by 25 papers in the map (data through 7 Oct 2026). Builds on 20 of its 48 references that are in the map. First posted on arXiv 15 Apr 2021.

Builds on

20 of 48 references.

References · 20

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 878
  3. 2018Pyramid Stereo Matching Networkcited by 486
  4. 2019Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matchingcited by 414
  5. 2017End-to-End Learning of Geometry and Context for Deep Stereo Regressioncited by 359
  6. 2019Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inferencecited by 252
  7. 2019GA-Net: Guided Aggregation Net for End-to-end Stereo Matchingcited by 242
  8. 2020AANet: Adaptive Aggregation Network for Efficient Stereo Matchingcited by 202
  9. 2019Deep Stereo using Adaptive Thin Volume Representation with Uncertainty Awarenesscited by 151
  10. 2019Point-Based Multi-View Stereo Networkcited by 147
  11. 2019Hierarchical Deep Stereo Matching on High-resolution Imagescited by 126
  12. 2019CARAFE: Content-Aware ReAssembly of FEaturescited by 119
8 more
  1. 2019DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatchcited by 114
  2. 2020Fast-MVSNet: Sparse-to-Dense Multi-View Stereo With Learned Propagation and Gauss-Newton Refinementcited by 105
  3. 2018Hierarchical Discrete Distribution Decomposition for Match Density Estimationcited by 93
  4. 2018StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Predictioncited by 88
  5. 2018Real-time self-adaptive deep stereocited by 80
  6. 2014Computing the Stereo Matching Cost with a Convolutional Neural Networkcited by 74
  7. 2020Bi3D: Stereo Depth Estimation via Binary Classificationscited by 34
  8. 2020A Novel Recurrent Encoder-Decoder Structure for Large-Scale Multi-view Stereo Reconstruction from An Open Aerial Datasetcited by 28

Built on by

Cited by year

Citing papers per year: 2022: 5; 2023: 3; 2024: 7; 2025: 10.

25 papers.

Sort:

By area:

  1. 2023Iterative Geometry Encoding Volume for Stereo Matchingcited by 188
  2. 2022Attention Concatenation Volume for Accurate and Efficient Stereo Matchingcited by 130
  3. 2022Accurate and Efficient Stereo Matching via Attention Concatenation Volumecited by 59
  4. 2024IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo Matchingcited by 55
  5. 2022Context-Enhanced Stereo Transformercited by 37
  6. 2023Uncertainty Guided Adaptive Warping for Robust and Efficient Stereo Matchingcited by 36
  7. 2024LightStereo: Channel Boost Is All You Need for Efficient 2D Cost Aggregationcited by 28
  8. 2024A Survey on Deep Stereo Matching in the Twentiescited by 23
  9. 2023CGI-Stereo: Accurate and Real-Time Stereo Matching via Context and Geometry Interactioncited by 17
  10. 2024BCLNet: Bilateral Consensus Learning for Two-View Correspondence Pruningcited by 12
  11. 2025BANet: Bilateral Aggregation Network for Mobile Stereo Matchingcited by 12
  12. 2024Learning Intra-view and Cross-view Geometric Knowledge for Stereo Matchingcited by 11
13 more
  1. 2022Depth Estimation by Combining Binocular Stereo and Monocular Structured-Lightcited by 4
  2. 2024DCVSMNet: Double Cost Volume Stereo Matching Networkcited by 3
  3. 2025Lite Any Stereo: Efficient Zero-Shot Stereo Matchingcited by 3
  4. 2022Accurate and Real-time Pseudo Lidar Detection: Is Stereo Neural Network Really Necessary?cited by 1
  5. 2025CorrMoE: Mixture of Experts with De-stylization Learning for Cross-Scene and Cross-Domain Correspondence Pruningcited by 1
  6. 2025MAFNet:Multi-frequency Adaptive Fusion Network for Real-time Stereo Matchingcited by 1
  7. 2024Ghost-Stereo: GhostNet-based Cost Volume Enhancement and Aggregation for Stereo Matching Networkscited by 0
  8. 2025Camera Movement Estimation and Path Correction using the Combination of Modified A-SIFT and Stereo System for 3D Modellingcited by 0
  9. 2025Distilling Stereo Networks for Performant and Efficient Leaner Networkscited by 0
  10. 2025LeanStereo: A Leaner Backbone based Stereo Networkcited by 0
  11. 2025ESMStereo: Enhanced ShuffleMixer Disparity Upsampling for Real-Time and Accurate Stereo Matchingcited by 0
  12. 2025Integrating Disparity Confidence Estimation into Relative Depth Prior-Guided Unsupervised Stereo Matchingcited by 0
  13. 2025Generalized Geometry Encoding Volume for Real-time Stereo Matchingcited by 0