mlsanityData to 14 Oct 2026

IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo

arXiv 2112.05126 ↗First posted 9 Dec 2021cs.CVcited by 56

Not on the map. Why?

Abstract (arXiv)

We present IterMVS, a new data-driven method for high-resolution multi-view stereo. We propose a novel GRU-based estimator that encodes pixel-wise probability distributions of depth in its hidden state. Ingesting multi-scale matching information, our model refines these distributions over multiple iterations and infers depth and confidence. To extract the depth maps, we combine traditional classification and regression in a novel manner. We verify the efficiency and effectiveness of our method on DTU, Tanks&Temples and ETH3D. While being the most efficient method in both memory and run-time, our model achieves competitive performance on DTU and better generalization ability on Tanks&Temples as well as ETH3D than most state-of-the-art methods. Code is available at https://github.com/FangjinhuaWang/IterMVS.

Key facts. Cited by 56 papers in the map (data through 14 Oct 2026). Builds on 30 of its 54 references that are in the map. First posted on arXiv 9 Dec 2021.

Builds on

30 of 54 references.

References · 30

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  4. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  5. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
  6. 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,436
  7. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 788
  8. 2019BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networkscited by 490
  9. 2019Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matchingcited by 417
  10. 2017End-to-End Learning of Geometry and Context for Deep Stereo Regressioncited by 360
  11. 2021RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matchingcited by 353
  12. 2019Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inferencecited by 254
18 more
  1. 2019Group-wise Correlation Stereo Networkcited by 235
  2. 2020PatchmatchNet: Learned Multi-View Patchmatch Stereocited by 207
  3. 2017Learning a Multi-View Stereo Machinecited by 194
  4. 2019Cost Volume Pyramid Based Depth Inference for Multi-View Stereocited by 154
  5. 2019Deep Stereo using Adaptive Thin Volume Representation with Uncertainty Awarenesscited by 151
  6. 2019Point-Based Multi-View Stereo Networkcited by 147
  7. 2017SurfaceNet: An End-to-end 3D Neural Network for Multiview Stereopsiscited by 128
  8. 2020RAFT-3D: Scene Flow using Rigid-Motion Embeddingscited by 122
  9. 2019Multi-Scale Geometric Consistency Guided Multi-View Stereocited by 105
  10. 2020Fast-MVSNet: Sparse-to-Dense Multi-View Stereo With Learned Propagation and Gauss-Newton Refinementcited by 105
  11. 2020Visibility-aware Multi-view Stereo Networkcited by 98
  12. 2020Dense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency Checkingcited by 81
  13. 2019Learning Inverse Depth Regression for Multi-View Stereo with Correlation Cost Volumecited by 59
  14. 2019Planar Prior Assisted PatchMatch Multi-View Stereocited by 57
  15. 2020PVSNet: Pixelwise Visibility-Aware Multi-View Stereo Networkcited by 35
  16. 2019DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstructioncited by 23
  17. 2021PatchMatch-RL: Deep MVS with Pixelwise Depth, Normal, and Visibilitycited by 17
  18. 2020Belief Propagation Reloaded: Learning BP-Layers for Labeling Problemscited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 9; 2023: 15; 2024: 17; 2025: 9; 2026: 6.

56 papers.

Sort:

By area:

  1. 2024DepthSplat: Connecting Gaussian Splatting and Depthcited by 286
  2. 2023Iterative Geometry Encoding Volume for Stereo Matchingcited by 190
  3. 2024SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videoscited by 102
  4. 2022VolRecon: Volume Rendering of Signed Ray Distance Functions for Generalizable Multi-View Reconstructioncited by 62
  5. 2024IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo Matchingcited by 59
  6. 2023IEBins: Iterative Elastic Bins for Monocular Depth Estimationcited by 54
  7. 2022MVSFormer: Multi-View Stereo by Learning Robust Image Features and Temperature-based Depthcited by 53
  8. 2022MVSTER: Epipolar Transformer for Efficient Multi-View Stereocited by 50
  9. 2024MoCha-Stereo: Motif Channel Attention Network for Stereo Matchingcited by 48
  10. 2022DiffuStereo: High Quality Human Reconstruction via Diffusion-based Stereo Using Sparse Camerascited by 43
  11. 2024LRM-Zero: Training Large Reconstruction Models with Synthesized Datacited by 35
  12. 2023UniSDF: Unifying Neural Representations for High-Fidelity 3D Reconstruction of Complex Scenes with Reflectionscited by 30
38 more
  1. 2024Adaptive Fusion of Single-View and Multi-View Depth for Autonomous Drivingcited by 30
  2. 2023Learning to Fuse Monocular and Multi-view Cues for Multi-frame Depth Estimation in Dynamic Scenescited by 25
  3. 2022WT-MVSNet: Window-based Transformers for Multi-view Stereocited by 20
  4. 2025MonSter++: Unified Stereo Matching, Multi-view Stereo, and Real-time Stereo with Monodepth Priorscited by 19
  5. 2024Learning-based Multi-View Stereo: A Surveycited by 18
  6. 2025ReSplat: Learning Recurrent Gaussian Splattingcited by 15
  7. 2022RIAV-MVS: Recurrent-Indexing an Asymmetric Volume for Multi-View Stereocited by 12
  8. 2022Crafting Monocular Cues and Velocity Guidance for Self-Supervised Multi-Frame Depth Learningcited by 12
  9. 2025SED-MVS: Segmentation-Driven and Edge-Aligned Deformation Multi-View Stereo with Depth Restoration and Occlusion Constraintcited by 11
  10. 2023CostFormer:Cost Transformer for Cost Aggregation in Multi-view Stereocited by 9
  11. 2023TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereocited by 9
  12. 2024ASGrasp: Generalizable Transparent Object Reconstruction and 6-DoF Grasp Detection from RGB-D Active Stereo Cameracited by 9
  13. 2023Hierarchical Prior Mining for Non-local Multi-View Stereocited by 7
  14. 2024UWStereo: A Large Synthetic Dataset for Underwater Stereo Matchingcited by 7
  15. 2024MVSDet: Multi-View Indoor 3D Object Detection via Efficient Plane Sweepscited by 7
  16. 2026D'ej`a View: Looping Transformers for Multi-View 3D Reconstructioncited by 6
  17. 2024RobustMVS: Single Domain Generalized Deep Multi-view Stereocited by 5
  18. 2024SG-NeRF: Neural Surface Reconstruction with Scene Graph Optimizationcited by 5
  19. 2026IDESplat: Iterative Depth Probability Estimation for Generalizable 3D Gaussian Splattingcited by 5
  20. 2023SCALAR-NeRF: SCAlable LARge-scale Neural Radiance Fields for Scene Reconstructioncited by 4
  21. 2025CL-MVSNet: Unsupervised Multi-view Stereo with Dual-level Contrastive Learningcited by 4
  22. 2025DVP-MVS++: Synergize Depth-Normal-Edge and Harmonized Visibility Prior for Multi-View Stereocited by 4
  23. 2025Lightweight and Accurate Multi-View Stereo with Confidence-Aware Diffusion Modelcited by 4
  24. 2022Rethinking Disparity: A Depth Range Free Multi-View Stereo Based on Disparitycited by 3
  25. 2022DELS-MVS: Deep Epipolar Line Search for Multi-View Stereocited by 3
  26. 2023Indoor Scene Reconstruction with Fine-Grained Details Using Hybrid Representation and Normal Prior Enhancementcited by 3
  27. 2024SDL-MVS: View Space and Depth Deformable Learning Paradigm for Multi-View Stereo Reconstruction in Remote Sensingcited by 3
  28. 2024A Global Depth-Range-Free Multi-View Stereo Transformer Network with Pose Embeddingcited by 3
  29. 2023Multi-View Stereo Representation Revisit: Region-Aware MVSNetcited by 2
  30. 2023ARAI-MVSNet: A multi-view stereo depth estimation network with adaptive depth range and depth intervalcited by 2
  31. 2023Exploiting Multiple Priors for Neural 3D Indoor Reconstructioncited by 2
  32. 2024MVS-GS: High-Quality 3D Gaussian Splatting Mapping via Online Multi-View Stereocited by 2
  33. 2025Towards Depth Foundation Model: Recent Trends in Vision-Based Depth Estimationcited by 2
  34. 2025MVSMamba: Multi-View Stereo with State Space Modelcited by 2
  35. 2023V-FUSE: Volumetric Depth Map Fusion with Long-Range Constraintscited by 1
  36. 2023GSDC Transformer: An Efficient and Effective Cue Fusion for Monocular Multi-Frame Depth Estimationcited by 1
  37. 2024VHS: High-Resolution Iterative Stereo Matching with Visual Hull Priorscited by 1
  38. 2026ImLoc: Revisiting Visual Localization with Image-based Representationcited by 1

50 most cited of 56 All 56 (JSON)