mlsanityData to 19 Oct 2026

Multi-view stereo and depth estimation

195 papers0 this weekLow confidence in this grouping: the papers may belong to more than one topic, or the group may changeLow confidence in this grouping: the papers may belong to more than one topic, or the group may change · About

Keywords: depth, stereo, mvs, multi-view stereo, multi-view

Key facts. Multi-view stereo and depth estimation: 195 papers on arXiv since 2021 (data through 19 Oct 2026). 43 of its 195 mapped papers (22%) cite “AA-RMVSNet: Adaptive Aggregation Recurrent Multi-view Stereo Network” (2021, arXiv 2108.03824).

What’s new

Nothing new since 1 Oct. Latest: 27 Sep 2026.

Foundations

Most cited by papers here

  1. AA-RMVSNet: Adaptive Aggregation Recurrent Multi-view Stereo Network2021cited by 43 here
  2. TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers2021cited by 37 here
  3. Rethinking Depth Estimation for Multi-View Stereo: A Unified Representation2022cited by 33 here
  4. IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo2021cited by 26 here
  5. Generalized Binary Search Network for Highly-Efficient Multi-View Stereo2021cited by 25 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2021AA-RMVSNet: Adaptive Aggregation Recurrent Multi-view Stereo Networkcited by 43 here
  2. 2021TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformerscited by 37 here
  3. 2022MVSTER: Epipolar Transformer for Efficient Multi-View Stereocited by 22 here
  4. 2022MVSFormer: Multi-View Stereo by Learning Robust Image Features and Temperature-based Depthcited by 21 here
  5. 2024MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereocited by 16 here
19 more it builds on, not in this chain
  1. 2021NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Videocited by 18 here
  2. 2021Self-supervised Learning of Depth Inference for Multi-view Stereocited by 11 here
  3. 2021Self-supervised Multi-view Stereo via Effective Co-Segmentation and Data-Augmentationcited by 13 here
  4. 2021MVS2D: Efficient Multi-view Stereo via Attention-Driven 2D Convolutionscited by 16 here
  5. 2021TransformerFusion: Monocular RGB Scene Reconstruction using Transformerscited by 11 here
  6. 2021PatchMatch-RL: Deep MVS with Pixelwise Depth, Normal, and Visibilitycited by 14 here
  7. 2021Digging into Uncertainty in Self-supervised Multi-view Stereocited by 12 here
  8. 2021Multi-View Stereo with Transformercited by 8 here
  9. 2021Generalized Binary Search Network for Highly-Efficient Multi-View Stereocited by 25 here
  10. 2021IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereocited by 26 here
  11. 2021Curvature-guided dynamic scale networks for Multi-view Stereocited by 11 here
  12. 2022Rethinking Depth Estimation for Multi-View Stereo: A Unified Representationcited by 33 here
  13. 2022RC-MVSNet: Unsupervised Multi-View Stereo with Neural Renderingcited by 8 here
  14. 2022Non-parametric Depth Distribution Modelling based Depth Inference for Multi-view Stereocited by 8 here
  15. 2022WT-MVSNet: Window-based Transformers for Multi-view Stereocited by 13 here
  16. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 10 here
  17. 2022SimpleRecon: 3D Reconstruction Without 3D Convolutionscited by 13 here
  18. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 21 here
  19. 2023DUSt3R: Geometric 3D Vision Made Easycited by 12 here

The 24 most cited of 415.

Browse

30 of 195, ranked 6–35

  1. 6MVSTER: Epipolar Transformer for Efficient Multi-View Stereo202222
  2. 7MVSFormer: Multi-View Stereo by Learning Robust Image Features and Temperature-based Depth202221
  3. 8MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereo202416
  4. 9MVS2D: Efficient Multi-view Stereo via Attention-Driven 2D Convolutions202116
  5. 10PatchMatch-RL: Deep MVS with Pixelwise Depth, Normal, and Visibility202114
  6. 11WT-MVSNet: Window-based Transformers for Multi-view Stereo202213
  7. 12Self-supervised Multi-view Stereo via Effective Co-Segmentation and Data-Augmentation202113
  8. 13Digging into Uncertainty in Self-supervised Multi-view Stereo202112
  9. 14Self-supervised Learning of Depth Inference for Multi-view Stereo202111
  10. 15Curvature-guided dynamic scale networks for Multi-view Stereo202111
All 30
  1. 16RayMVSNet++: Learning Ray-based 1D Implicit Fields for Accurate Multi-View Stereo20238
  2. 17When Epipolar Constraint Meets Non-local Operators in Multi-View Stereo20238
  3. 18RC-MVSNet: Unsupervised Multi-View Stereo with Neural Rendering20228
  4. 19Non-parametric Depth Distribution Modelling based Depth Inference for Multi-view Stereo20228
  5. 20Multi-View Stereo with Transformer20218
  6. 21GoMVS: Geometrically Consistent Cost Aggregation for Multi-View Stereo20247
  7. 22VolumeFusion: Deep Depth Fusion for 3D Scene Reconstruction20217
  8. 23SD-MVS: Segmentation-Driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization20246
  9. 24Deep Multi-View Stereo gone wild20216
  10. 25MVSAnywhere: Zero-Shot Multi-View Stereo20255
  11. 26Hierarchical Prior Mining for Non-local Multi-View Stereo20235
  12. 27Non-local Recurrent Regularization Networks for Multi-view Stereo20215
  13. 28Multi-view Reconstruction via SfM-guided Monocular Depth Estimation20254
  14. 29Learning-based Multi-View Stereo: A Survey20244
  15. 30CostFormer:Cost Transformer for Cost Aggregation in Multi-view Stereo20234
  16. 31Constraining Depth Map Geometry for Multi-View Stereo: A Dual-Depth Approach with Saddle-shaped Depth Cells20234
  17. 32GC-MVSNet: Multi-View, Multi-Scale, Geometrically-Consistent Multi-View Stereo20234
  18. 33RIAV-MVS: Recurrent-Indexing an Asymmetric Volume for Multi-View Stereo20224
  19. 34DS-MVSNet: Unsupervised Multi-view Stereo via Depth Synthesis20224
  20. 35A Benchmark and a Baseline for Robust Multi-view Depth Estimation20224