mlsanityData to 7 Oct 2026

Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching

arXiv 1912.06378 ↗First posted 13 Dec 2019cs.CVcited by 414

Not on the map. Why?

Abstract (arXiv)

The deep multi-view stereo (MVS) and stereo matching approaches generally construct 3D cost volumes to regularize and regress the output depth or disparity. These methods are limited when high-resolution outputs are needed since the memory and time costs grow cubically as the volume resolution increases. In this paper, we propose a both memory and time efficient cost volume formulation that is complementary to existing multi-view stereo and stereo matching approaches based on 3D cost volumes. First, the proposed cost volume is built upon a standard feature pyramid encoding geometry and context at gradually finer scales. Then, we can narrow the depth (or disparity) range of each stage by the depth (or disparity) map from the previous stage. With gradually higher cost volume resolution and adaptive adjustment of depth (or disparity) intervals, the output is recovered in a coarser to fine manner. We apply the cascade cost volume to the representative MVS-Net, and obtain a 23.1% improvement on DTU benchmark (1st place), with 50.6% and 74.2% reduction in GPU memory and run-time. It is also the state-of-the-art learning-based method on Tanks and Temples benchmark. The statistics of accuracy, run-time and GPU memory on other representative stereo CNNs also validate the effectiveness of our proposed method.

Key facts. Cited by 414 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 52; 2022: 68; 2023: 77; 2024: 85; 2025: 82; 2026: 50.

414 papers.

Sort:

By area:

  1. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  2. 2025VGGT: Visual Geometry Grounded Transformercited by 1,475
  3. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 735
  4. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 568
  5. 2024MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Imagescited by 553
  6. 2024GS-LRM: Large Reconstruction Model for 3D Gaussian Splattingcited by 344
  7. 2023FSGS: Real-Time Few-shot View Synthesis using Gaussian Splattingcited by 278
  8. 2024DepthSplat: Connecting Gaussian Splatting and Depthcited by 275
  9. 2022Unifying Flow, Stereo and Depth Estimationcited by 270
  10. 2021NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Videocited by 241
  11. 2021GeoNeRF: Generalizing NeRF with Geometry Priorscited by 195
  12. 2021The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depthcited by 190
38 more
  1. 2023Iterative Geometry Encoding Volume for Stereo Matchingcited by 188
  2. 2022SparseNeuS: Fast Generalizable Neural Surface Reconstruction from Sparse Viewscited by 175
  3. 2022SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Imagecited by 165
  4. 2025VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstructioncited by 154
  5. 2021CFNet: Cascade and Fused Cost Volume for Robust Stereo Matchingcited by 153
  6. 2021Efficient Neural Radiance Fields for Interactive Free-viewpoint Videocited by 150
  7. 2025Streaming 4D Visual Geometry Transformercited by 147
  8. 2021Improving neural implicit surfaces geometry with patch warpingcited by 136
  9. 2024MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Secondscited by 136
  10. 2022Attention Concatenation Volume for Accurate and Efficient Stereo Matchingcited by 130
  11. 2022Neural 3D Scene Reconstruction with the Manhattan-world Assumptioncited by 123
  12. 2021SMD-Nets: Stereo Mixture Density Networkscited by 118
  13. 2021TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformerscited by 117
  14. 2024RaDe-GS: Rasterizing Depth in Gaussian Splattingcited by 110
  15. 2022NeRFusion: Fusing Radiance Fields for Large-Scale Scene Reconstructioncited by 99
  16. 2022BEVStereo: Enhancing Depth Estimation in Multi-view 3D Object Detection with Dynamic Temporal Stereocited by 89
  17. 2022SimpleRecon: 3D Reconstruction Without 3D Convolutionscited by 83
  18. 2022Rethinking Depth Estimation for Multi-View Stereo: A Unified Representationcited by 82
  19. 2025Point3R: Streaming 3D Reconstruction with Explicit Spatial Pointer Memorycited by 82
  20. 2022Neural 3D Reconstruction in the Wildcited by 79
  21. 2021Learning Signed Distance Field for Multi-view Surface Reconstructioncited by 76
  22. 2024Large Spatial Model: End-to-end Unposed Images to Semantic 3Dcited by 73
  23. 2021AA-RMVSNet: Adaptive Aggregation Recurrent Multi-view Stereo Networkcited by 71
  24. 2024TranSplat: Generalizable 3D Gaussian Splatting from Sparse Multi-View Images with Transformerscited by 71
  25. 2021Category-Level 6D Object Pose Estimation via Cascaded Relation and Recurrent Reconstruction Networkscited by 69
  26. 2025Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priorscited by 69
  27. 2022Unified Implicit Neural Stylizationcited by 67
  28. 2024InstantSplat: Sparse-view Gaussian Splatting in Secondscited by 67
  29. 2024GS2Mesh: Surface Reconstruction from Gaussian Splatting via Novel Stereo Viewscited by 65
  30. 2022NeuralUDF: Learning Unsigned Distance Fields for Multi-view Reconstruction of Surfaces with Arbitrary Topologiescited by 62
  31. 2022VolRecon: Volume Rendering of Signed Ray Distance Functions for Generalizable Multi-View Reconstructioncited by 61
  32. 2023DBARF: Deep Bundle-Adjusting Generalizable Neural Radiance Fieldscited by 60
  33. 2022Accurate and Efficient Stereo Matching via Attention Concatenation Volumecited by 59
  34. 2021IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereocited by 56
  35. 2024IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo Matchingcited by 55
  36. 2024LaRa: Efficient Large-Baseline Radiance Fieldscited by 54
  37. 2022STS: Surround-view Temporal Stereo for Multi-view 3D Detectioncited by 53
  38. 2022Multiview Stereo with Cascaded Epipolar RAFTcited by 51

50 most cited of 414 All 414 (JSON)