mlsanityData to 7 Oct 2026

SurfaceNet: An End-to-end 3D Neural Network for Multiview Stereopsis

arXiv 1708.01749 ↗First posted 5 Aug 2017cs.CVcited by 128

Not on the map. Why?

Abstract (arXiv)

This paper proposes an end-to-end learning framework for multiview stereopsis. We term the network SurfaceNet. It takes a set of images and their corresponding camera parameters as input and directly infers the 3D model. The key advantage of the framework is that both photo-consistency as well geometric relations of the surface structure can be directly learned for the purpose of multiview stereopsis in an end-to-end fashion. SurfaceNet is a fully 3D convolutional network which is achieved by encoding the camera parameters together with the images in a 3D voxel representation. We evaluate SurfaceNet on the large-scale DTU benchmark.

Key facts. Cited by 128 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Aug 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 37; 2022: 35; 2023: 26; 2024: 13; 2025: 15; 2026: 2.

128 papers.

Sort:

By area:

  1. 2022TensoRF: Tensorial Radiance Fieldscited by 1,275
  2. 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
  3. 2023SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Drivingcited by 310
  4. 2021NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Videocited by 241
  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 177
  7. 2022SparseNeuS: Fast Generalizable Neural Surface Reconstruction from Sparse Viewscited by 175
  8. 2021Improving neural implicit surfaces geometry with patch warpingcited by 136
  9. 2021TransformerFusion: Monocular RGB Scene Reconstruction using Transformerscited by 107
  10. 2022NeRFusion: Fusing Radiance Fields for Large-Scale Scene Reconstructioncited by 99
  11. 2021NeuTex: Neural Texture Mapping for Volumetric Neural Renderingcited by 98
  12. 2021Bidirectional Projection Network for Cross Dimension Scene Understandingcited by 95
38 more
  1. 2022SimpleRecon: 3D Reconstruction Without 3D Convolutionscited by 83
  2. 2022Rethinking Depth Estimation for Multi-View Stereo: A Unified Representationcited by 82
  3. 2023StyleRF: Zero-shot 3D Style Transfer of Neural Radiance Fieldscited by 79
  4. 2021AA-RMVSNet: Adaptive Aggregation Recurrent Multi-view Stereo Networkcited by 71
  5. 2023Ref-NeuS: Ambiguity-Reduced Neural Implicit Surface Learning for Multi-View Reconstruction with Reflectioncited by 68
  6. 2022NeuralUDF: Learning Unsigned Distance Fields for Multi-view Reconstruction of Surfaces with Arbitrary Topologiescited by 62
  7. 2021IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereocited by 56
  8. 2022Multiview Stereo with Cascaded Epipolar RAFTcited by 51
  9. 2022MVSFormer: Multi-View Stereo by Learning Robust Image Features and Temperature-based Depthcited by 50
  10. 2022GIFS: Neural Implicit Function for General Shape Representationcited by 45
  11. 2021VolumeFusion: Deep Depth Fusion for 3D Scene Reconstructioncited by 44
  12. 2021MVS2D: Efficient Multi-view Stereo via Attention-Driven 2D Convolutionscited by 43
  13. 2023NeuralEditor: Editing Neural Radiance Fields via Manipulating Point Cloudscited by 41
  14. 2021TANDEM: Tracking and Dense Mapping in Real-time using Deep Multi-view Stereocited by 39
  15. 2021VoRTX: Volumetric 3D Reconstruction With Transformers for Voxelwise View Selection and Fusioncited by 38
  16. 2023Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitivescited by 37
  17. 2023NeuSurf: On-Surface Priors for Neural Surface Reconstruction from Sparse Input Viewscited by 36
  18. 2021Generalized Binary Search Network for Highly-Efficient Multi-View Stereocited by 32
  19. 2021Self-supervised Multi-view Stereo via Effective Co-Segmentation and Data-Augmentationcited by 31
  20. 2021Digging into Uncertainty in Self-supervised Multi-view Stereocited by 31
  21. 2021Input-level Inductive Biases for 3D Reconstructioncited by 31
  22. 2021Continual Neural Mapping: Learning An Implicit Scene Representation from Sequential Observationscited by 30
  23. 2022Uncertainty-Aware Deep Multi-View Photometric Stereocited by 30
  24. 2022RC-MVSNet: Unsupervised Multi-View Stereo with Neural Renderingcited by 30
  25. 2025FatesGS: Fast and Accurate Sparse-View Surface Reconstruction using Gaussian Splatting with Depth-Feature Consistencycited by 30
  26. 2022PlaneMVS: 3D Plane Reconstruction from Multi-View Stereocited by 29
  27. 2021Neural Radiance Fields Approach to Deep Multi-View Photometric Stereocited by 25
  28. 2024UFORecon: Generalizable Sparse-View Surface Reconstruction from Arbitrary and UnFavOrable Setscited by 22
  29. 2021Outdoor inverse rendering from a single image using multiview self-supervisioncited by 18
  30. 2023MVPSNet: Fast Generalizable Multi-view Photometric Stereocited by 18
  31. 2024PixelGaussian: Generalizable 3D Gaussian Reconstruction from Arbitrary Viewscited by 18
  32. 2021PatchMatch-RL: Deep MVS with Pixelwise Depth, Normal, and Visibilitycited by 17
  33. 2021Curvature-guided dynamic scale networks for Multi-view Stereocited by 17
  34. 2022MonoNeuralFusion: Online Monocular Neural 3D Reconstruction with Geometric Priorscited by 17
  35. 20213DRIMR: 3D Reconstruction and Imaging via mmWave Radar based on Deep Learningcited by 16
  36. 2021NeeDrop: Self-supervised Shape Representation from Sparse Point Clouds using Needle Droppingcited by 16
  37. 2023Neural Vector Fields: Implicit Representation by Explicit Learningcited by 16
  38. 2023RayMVSNet++: Learning Ray-based 1D Implicit Fields for Accurate Multi-View Stereocited by 15

50 most cited of 128 All 128 (JSON)