mlsanityData to 14 Oct 2026

ShadowNeuS: Neural SDF Reconstruction by Shadow Ray Supervision

arXiv 2211.14086 ↗First posted 25 Nov 2022cs.CVcited by 17

Not on the map. Why?

Abstract (arXiv)

By supervising camera rays between a scene and multi-view image planes, NeRF reconstructs a neural scene representation for the task of novel view synthesis. On the other hand, shadow rays between the light source and the scene have yet to be considered. Therefore, we propose a novel shadow ray supervision scheme that optimizes both the samples along the ray and the ray location. By supervising shadow rays, we successfully reconstruct a neural SDF of the scene from single-view images under multiple lighting conditions. Given single-view binary shadows, we train a neural network to reconstruct a complete scene not limited by the camera's line of sight. By further modeling the correlation between the image colors and the shadow rays, our technique can also be effectively extended to RGB inputs. We compare our method with previous works on challenging tasks of shape reconstruction from single-view binary shadow or RGB images and observe significant improvements. The code and data are available at https://github.com/gerwang/ShadowNeuS.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Builds on 36 of its 65 references that are in the map. First posted on arXiv 25 Nov 2022.

Builds on

36 of 65 references.

References · 36

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  3. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  4. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  5. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
  6. 2021Volume Rendering of Neural Implicit Surfacescited by 996
  7. 2020Implicit Geometric Regularization for Learning Shapescited by 710
  8. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 700
  9. 2021UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstructioncited by 646
  10. 2021BARF: Bundle-Adjusting Neural Radiance Fieldscited by 642
  11. 2021Neural Fields in Visual Computing and Beyondcited by 540
  12. 2020NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesiscited by 496
24 more
  1. 2021Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesiscited by 464
  2. 2020NeRD: Neural Reflectance Decomposition from Image Collectionscited by 449
  3. 2020Modular Primitives for High-Performance Differentiable Renderingcited by 441
  4. 2021PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relightingcited by 335
  5. 2021Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decompositioncited by 205
  6. 2020Neural Reflectance Fields for Appearance Acquisitioncited by 196
  7. 2022Modeling Indirect Illumination for Inverse Renderingcited by 168
  8. 2022SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Imagecited by 165
  9. 2021NeRF--: Neural Radiance Fields Without Known Camera Parameterscited by 155
  10. 2021NeRFactor: Neural Factorization of Shape and Reflectance Under an Unknown Illuminationcited by 135
  11. 2022IRON: Inverse Rendering by Optimizing Neural SDFs and Materials from Photometric Imagescited by 111
  12. 2022NeILF: Neural Incident Light Field for Physically-based Material Estimationcited by 105
  13. 2020Deep Reflectance Volumes: Relightable Reconstructions from Multi-View Photometric Imagescited by 98
  14. 2019Controlling Neural Level Setscited by 76
  15. 2022PS-NeRF: Neural Inverse Rendering for Multi-view Photometric Stereocited by 69
  16. 2019Self-calibrating Deep Photometric Stereo Networkscited by 47
  17. 2021Non-line-of-Sight Imaging via Neural Transient Fieldscited by 41
  18. 2022Relighting4D: Neural Relightable Human from Videoscited by 41
  19. 2022S3-NeRF: Neural Reflectance Field from Shading and Shadow under a Single Viewpointcited by 30
  20. 2022Neural Reflectance for Shape Recovery with Shadow Handlingcited by 28
  21. 20223PSDF: Three-Pole Signed Distance Function for Learning Surfaces with Arbitrary Topologiescited by 27
  22. 2022Differentiable Rendering of Neural SDFs through Reparameterizationcited by 26
  23. 2022Towards Learning Neural Representations from Shadowscited by 12
  24. 2022DeepShadow: Neural Shape from Shadowcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 8; 2024: 6; 2025: 1; 2026: 2.

17 papers.

Sort:

  1. 2023StreetSurf: Extending Multi-view Implicit Surface Reconstruction to Street Viewscited by 120
  2. 2023NeILF++: Inter-Reflectable Light Fields for Geometry and Material Estimationcited by 74
  3. 2023NeISF: Neural Incident Stokes Field for Geometry and Material Estimationcited by 25
  4. 2024OmniSR: Shadow Removal under Direct and Indirect Lightingcited by 19
  5. 20243D Reconstruction with Fast Dipole Sumscited by 12
  6. 2023NeuDA: Neural Deformable Anchor for High-Fidelity Implicit Surface Reconstructioncited by 10
  7. 2023High-Quality Facial Geometry and Appearance Capture at Homecited by 9
  8. 2023PlatoNeRF: 3D Reconstruction in Plato's Cave via Single-View Two-Bounce Lidarcited by 9
  9. 2024NeRF as a Non-Distant Environment Emitter in Physics-based Inverse Renderingcited by 8
  10. 2023Fast Sun-aligned Outdoor Scene Relighting based on TensoRFcited by 7
  11. 2025S-EO: A Large-Scale Dataset for Geometry-Aware Shadow Detection in Remote Sensing Applicationscited by 5
  12. 2024PIR: Photometric Inverse Rendering with Shading Cues Modeling and Surface Reflectance Regularizationcited by 2
5 more
  1. 2024MLI-NeRF: Multi-Light Intrinsic-Aware Neural Radiance Fieldscited by 1
  2. 2023Survey on Controlable Image Synthesis with Deep Learningcited by 0
  3. 2024Learning Relighting and Intrinsic Decomposition in Neural Radiance Fieldscited by 0
  4. 2026Soft Shadow Diffusion (SSD): Physics-inspired Learning for 3D Computational Periscopycited by 0
  5. 2026RehearsalNeRF: Decoupling Intrinsic Neural Fields of Dynamic Illuminations for Scene Editingcited by 0