mlsanityData to 7 Oct 2026

PatchmatchNet: Learned Multi-View Patchmatch Stereo

arXiv 2012.01411 ↗First posted 2 Dec 2020cs.CVcited by 204

Not on the map. Why?

Abstract (arXiv)

We present PatchmatchNet, a novel and learnable cascade formulation of Patchmatch for high-resolution multi-view stereo. With high computation speed and low memory requirement, PatchmatchNet can process higher resolution imagery and is more suited to run on resource limited devices than competitors that employ 3D cost volume regularization. For the first time we introduce an iterative multi-scale Patchmatch in an end-to-end trainable architecture and improve the Patchmatch core algorithm with a novel and learned adaptive propagation and evaluation scheme for each iteration. Extensive experiments show a very competitive performance and generalization for our method on DTU, Tanks & Temples and ETH3D, but at a significantly higher efficiency than all existing top-performing models: at least two and a half times faster than state-of-the-art methods with twice less memory usage.

Key facts. Cited by 204 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 43; 2023: 44; 2024: 42; 2025: 38; 2026: 25.

204 papers.

Sort:

By area:

  1. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  2. 2025VGGT: Visual Geometry Grounded Transformercited by 1,475
  3. 2024Grounding Image Matching in 3D with MASt3Rcited by 960
  4. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 568
  5. 2024PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstructioncited by 280
  6. 2024DepthSplat: Connecting Gaussian Splatting and Depthcited by 275
  7. 2023Iterative Geometry Encoding Volume for Stereo Matchingcited by 188
  8. 2025FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Viewscited by 176
  9. 2023NeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview Imagescited by 163
  10. 2024MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motioncited by 161
  11. 2024MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Secondscited by 136
  12. 2022Attention Concatenation Volume for Accurate and Efficient Stereo Matchingcited by 130
38 more
  1. 2021TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformerscited by 117
  2. 2023DNA-Rendering: A Diverse Neural Actor Repository for High-Fidelity Human-centric Renderingcited by 103
  3. 2022LaMAR: Benchmarking Localization and Mapping for Augmented Realitycited by 98
  4. 2022BEVStereo: Enhancing Depth Estimation in Multi-view 3D Object Detection with Dynamic Temporal Stereocited by 89
  5. 2022Rethinking Depth Estimation for Multi-View Stereo: A Unified Representationcited by 82
  6. 2021Learning Signed Distance Field for Multi-view Surface Reconstructioncited by 76
  7. 2023Ref-NeuS: Ambiguity-Reduced Neural Implicit Surface Learning for Multi-View Reconstruction with Reflectioncited by 68
  8. 2024GS2Mesh: Surface Reconstruction from Gaussian Splatting via Novel Stereo Viewscited by 65
  9. 2022VolRecon: Volume Rendering of Signed Ray Distance Functions for Generalizable Multi-View Reconstructioncited by 61
  10. 2021IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereocited by 56
  11. 2023Urban Radiance Field Representation with Deformable Neural Mesh Primitivescited by 55
  12. 2023VA-DepthNet: A Variational Approach to Single Image Depth Predictioncited by 54
  13. 2022STS: Surround-view Temporal Stereo for Multi-view 3D Detectioncited by 53
  14. 2022MVSTER: Epipolar Transformer for Efficient Multi-View Stereocited by 50
  15. 2022MVSFormer: Multi-View Stereo by Learning Robust Image Features and Temperature-based Depthcited by 50
  16. 2024MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereocited by 49
  17. 2024MoCha-Stereo: Motif Channel Attention Network for Stereo Matchingcited by 48
  18. 2023RenderMe-360: A Large Digital Asset Library and Benchmarks Towards High-fidelity Head Avatarscited by 45
  19. 2021MVS2D: Efficient Multi-view Stereo via Attention-Driven 2D Convolutionscited by 43
  20. 2022DIP: Deep Inverse Patchmatch for High-Resolution Optical Flowcited by 40
  21. 2022FWD: Real-time Novel View Synthesis with Forward Warping and Depthcited by 39
  22. 2025Matrix3D: Large Photogrammetry Model All-in-Onecited by 39
  23. 2022A Benchmark and a Baseline for Robust Multi-view Depth Estimationcited by 38
  24. 2024LRM-Zero: Training Large Reconstruction Models with Synthesized Datacited by 35
  25. 2021Generalized Binary Search Network for Highly-Efficient Multi-View Stereocited by 32
  26. 2024Hierarchical Temporal Context Learning for Camera-based Semantic Scene Completioncited by 32
  27. 2025WinT3R: Window-Based Streaming Reconstruction with Camera Token Poolcited by 32
  28. 2021Digging into Uncertainty in Self-supervised Multi-view Stereocited by 31
  29. 2022Uncertainty-Aware Deep Multi-View Photometric Stereocited by 30
  30. 2022RC-MVSNet: Unsupervised Multi-View Stereo with Neural Renderingcited by 30
  31. 2024Adaptive Fusion of Single-View and Multi-View Depth for Autonomous Drivingcited by 30
  32. 2025ReconViaGen: Towards Accurate Multi-view 3D Object Reconstruction via Generationcited by 30
  33. 2022PlaneMVS: 3D Plane Reconstruction from Multi-View Stereocited by 29
  34. 2023UniSDF: Unifying Neural Representations for High-Fidelity 3D Reconstruction of Complex Scenes with Reflectionscited by 29
  35. 2022PlanarRecon: Real-time 3D Plane Detection and Reconstruction from Posed Monocular Videoscited by 27
  36. 2025MVSAnywhere: Zero-Shot Multi-View Stereocited by 26
  37. 2025CityGS-X: A Scalable Architecture for Efficient and Geometrically Accurate Large-Scale Scene Reconstructioncited by 26
  38. 2021Neural Radiance Fields Approach to Deep Multi-View Photometric Stereocited by 25

50 most cited of 204 All 204 (JSON)