mlsanityData to 13 Oct 2026

Learning a Multi-View Stereo Machine

arXiv 1708.05375 ↗First posted 17 Aug 2017cs.CVcited by 194

Not on the map. Why?

Abstract (arXiv)

We present a learnt system for multi-view stereopsis. In contrast to recent learning based methods for 3D reconstruction, we leverage the underlying 3D geometry of the problem through feature projection and unprojection along viewing rays. By formulating these operations in a differentiable manner, we are able to learn the system end-to-end for the task of metric 3D reconstruction. End-to-end learning allows us to jointly reason about shape priors while conforming geometric constraints, enabling reconstruction from much fewer images (even a single image) than required by classical approaches as well as completion of unseen surfaces. We thoroughly evaluate our approach on the ShapeNet dataset and demonstrate the benefits over classical approaches as well as recent learning based methods.

Key facts. Cited by 194 papers in the map (data through 13 Oct 2026). First posted on arXiv 17 Aug 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 61; 2022: 50; 2023: 30; 2024: 28; 2025: 21; 2026: 4.

194 papers.

Sort:

By area:

  1. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,706
  2. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,610
  3. 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 905
  4. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 700
  5. 2023Scaffold-GS: Structured 3D Gaussians for View-Adaptive Renderingcited by 690
  6. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 648
  7. 2025Continuous 3D Perception Model with Persistent Statecited by 534
  8. 2021CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fieldscited by 370
  9. 2021Advances in Neural Renderingcited by 365
  10. 2021ABO: Dataset and Benchmarks for Real-World 3D Object Understandingcited by 363
  11. 2021Neural RGB-D Surface Reconstructioncited by 311
  12. 2021Mixture of Volumetric Primitives for Efficient Neural Renderingcited by 277
38 more
  1. 2021NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Videocited by 241
  2. 2022Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstructioncited by 211
  3. 2021Neural Articulated Radiance Fieldcited by 196
  4. 2021NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereocited by 191
  5. 2021The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depthcited by 190
  6. 2022Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detectioncited by 178
  7. 2022SparseNeuS: Fast Generalizable Neural Surface Reconstruction from Sparse Viewscited by 176
  8. 2021MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesiscited by 133
  9. 2021Unconstrained Scene Generation with Locally Conditioned Radiance Fieldscited by 130
  10. 2021Pathdreamer: A World Model for Indoor Navigationcited by 117
  11. 2023S-NeRF: Neural Radiance Fields for Street Viewscited by 116
  12. 2024Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Imagecited by 114
  13. 2024Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splatscited by 111
  14. 2022EfficientNeRF: Efficient Neural Radiance Fieldscited by 110
  15. 2021Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networkscited by 103
  16. 2022NeRFusion: Fusing Radiance Fields for Large-Scale Scene Reconstructioncited by 100
  17. 2023PC2: Projection-Conditioned Point Cloud Diffusion for Single-Image 3D Reconstructioncited by 84
  18. 2022SimpleRecon: 3D Reconstruction Without 3D Convolutionscited by 83
  19. 2022Rethinking Depth Estimation for Multi-View Stereo: A Unified Representationcited by 82
  20. 2021H3D-Net: Few-Shot High-Fidelity 3D Head Reconstructioncited by 81
  21. 2021Learning Signed Distance Field for Multi-view Surface Reconstructioncited by 76
  22. 2025RayZer: A Self-supervised Large View Synthesis Modelcited by 75
  23. 2021AA-RMVSNet: Adaptive Aggregation Recurrent Multi-view Stereo Networkcited by 71
  24. 2023Ref-NeuS: Ambiguity-Reduced Neural Implicit Surface Learning for Multi-View Reconstruction with Reflectioncited by 68
  25. 2021Unsupervised Learning of 3D Object Categories from Videos in the Wildcited by 67
  26. 2024You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scalecited by 65
  27. 2022Multi-Frame Self-Supervised Depth with Transformerscited by 64
  28. 2022NeuralUDF: Learning Unsigned Distance Fields for Multi-view Reconstruction of Surfaces with Arbitrary Topologiescited by 62
  29. 2021IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereocited by 56
  30. 2021Sketch2Model: View-Aware 3D Modeling from Single Free-Hand Sketchescited by 54
  31. 2022Few-View Object Reconstruction with Unknown Categories and Camera Posescited by 53
  32. 2023NeO 360: Neural Fields for Sparse View Synthesis of Outdoor Scenescited by 53
  33. 2021Multi-view 3D Reconstruction with Transformercited by 52
  34. 2022Multiview Stereo with Cascaded Epipolar RAFTcited by 51
  35. 2022GIFS: Neural Implicit Function for General Shape Representationcited by 45
  36. 2021UnsupervisedR&R: Unsupervised Point Cloud Registration via Differentiable Renderingcited by 44
  37. 2021MVS2D: Efficient Multi-view Stereo via Attention-Driven 2D Convolutionscited by 43
  38. 2021Full Surround Monodepth from Multiple Camerascited by 41

50 most cited of 194 All 194 (JSON)