mlsanityData to 7 Oct 2026

MVSNet: Depth Inference for Unstructured Multi-view Stereo

arXiv 1804.02505 ↗First posted 7 Apr 2018cs.CVcited by 780

Not on the map. Why?

Cited by 26 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We present an end-to-end deep learning architecture for depth map inference from multi-view images. In the network, we first extract deep visual image features, and then build the 3D cost volume upon the reference camera frustum via the differentiable homography warping. Next, we apply 3D convolutions to regularize and regress the initial depth map, which is then refined with the reference image to generate the final output. Our framework flexibly adapts arbitrary N-view inputs using a variance-based cost metric that maps multiple features into one cost feature. The proposed MVSNet is demonstrated on the large-scale indoor DTU dataset. With simple post-processing, our method not only significantly outperforms previous state-of-the-arts, but also is several times faster in runtime. We also evaluate MVSNet on the complex outdoor Tanks and Temples dataset, where our method ranks first before April 18, 2018 without any fine-tuning, showing the strong generalization ability of MVSNet.

Key facts. Cited by 780 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 73; 2022: 123; 2023: 155; 2024: 169; 2025: 148; 2026: 112.

780 papers.

Sort:

By area:

  1. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  2. 2025VGGT: Visual Geometry Grounded Transformercited by 1,475
  3. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,061
  4. 2024Grounding Image Matching in 3D with MASt3Rcited by 960
  5. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 735
  6. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 643
  7. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Imagecited by 638
  8. 2025Depth Anything 3: Recovering the Visual Space from Any Viewscited by 626
  9. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 568
  10. 2024MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Imagescited by 553
  11. 2025Continuous 3D Perception Model with Persistent Statecited by 527
  12. 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
38 more
  1. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 467
  2. 2023Neuralangelo: High-Fidelity Neural Surface Reconstructioncited by 464
  3. 2023Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priorscited by 395
  4. 2021RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matchingcited by 348
  5. 2024GS-LRM: Large Reconstruction Model for 3D Gaussian Splattingcited by 344
  6. 2021Neural RGB-D Surface Reconstructioncited by 312
  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. 20243D Reconstruction with Spatial Memorycited by 269
  11. 2021NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Videocited by 241
  12. 2024Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenescited by 226
  13. 2023MVImgNet: A Large-scale Dataset of Multi-view Imagescited by 219
  14. 2022Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstructioncited by 211
  15. 2021Pixel-Perfect Structure-from-Motion with Featuremetric Refinementcited by 199
  16. 2024GaussianPro: 3D Gaussian Splatting with Progressive Propagationcited by 199
  17. 2021GeoNeRF: Generalizing NeRF with Geometry Priorscited by 195
  18. 2021Neural Rays for Occlusion-aware Image-based Renderingcited by 192
  19. 2021The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depthcited by 190
  20. 2022NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fieldscited by 188
  21. 2023Iterative Geometry Encoding Volume for Stereo Matchingcited by 188
  22. 2022Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detectioncited by 177
  23. 2025FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Viewscited by 176
  24. 2022SparseNeuS: Fast Generalizable Neural Surface Reconstruction from Sparse Viewscited by 175
  25. 2022SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Imagecited by 165
  26. 2023NeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview Imagescited by 163
  27. 2022Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusioncited by 161
  28. 2022NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)cited by 156
  29. 2025VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstructioncited by 154
  30. 2021Efficient Neural Radiance Fields for Interactive Free-viewpoint Videocited by 150
  31. 2022NeuralLift-360: Lifting An In-the-wild 2D Photo to A 3D Object with 360deg Viewscited by 148
  32. 2023DynamicStereo: Consistent Dynamic Depth from Stereo Videoscited by 147
  33. 2024MeshLRM: Large Reconstruction Model for High-Quality Meshescited by 138
  34. 2023NeuSG: Neural Implicit Surface Reconstruction with 3D Gaussian Splatting Guidancecited by 137
  35. 2021Improving neural implicit surfaces geometry with patch warpingcited by 136
  36. 2024MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Secondscited by 136
  37. 2024Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Imagecited by 132
  38. 2022Neural 3D Scene Reconstruction with the Manhattan-world Assumptioncited by 123

50 most cited of 780 All 780 (JSON)