mlsanityData to 7 Oct 2026

Self-calibrating Deep Photometric Stereo Networks

arXiv 1903.07366 ↗First posted 18 Mar 2019cs.CVcited by 47

Not on the map. Why?

Abstract (arXiv)

This paper proposes an uncalibrated photometric stereo method for non-Lambertian scenes based on deep learning. Unlike previous approaches that heavily rely on assumptions of specific reflectances and light source distributions, our method is able to determine both shape and light directions of a scene with unknown arbitrary reflectances observed under unknown varying light directions. To achieve this goal, we propose a two-stage deep learning architecture, called SDPS-Net, which can effectively take advantage of intermediate supervision, resulting in reduced learning difficulty compared to a single-stage model. Experiments on both synthetic and real datasets show that our proposed approach significantly outperforms previous uncalibrated photometric stereo methods.

Key facts. Cited by 47 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Mar 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 17; 2023: 6; 2024: 7; 2025: 10; 2026: 1.

47 papers.

Sort:

By area:

  1. 2022PS-NeRF: Neural Inverse Rendering for Multi-view Photometric Stereocited by 69
  2. 2024MeshFormer: High-Quality Mesh Generation with 3D-Guided Reconstruction Modelcited by 55
  3. 2021Shape from Polarization for Complex Scenes in the Wildcited by 53
  4. 2021Shape and Material Capture at Homecited by 36
  5. 2021Robust Reflection Removal with Reflection-free Flash-only Cuescited by 34
  6. 2022Uncertainty-Aware Deep Multi-View Photometric Stereocited by 30
  7. 2022S3-NeRF: Neural Reflectance Field from Shading and Shadow under a Single Viewpointcited by 30
  8. 2023Scalable, Detailed and Mask-Free Universal Photometric Stereocited by 30
  9. 2021Neural Radiance Fields Approach to Deep Multi-View Photometric Stereocited by 25
  10. 2022Universal Photometric Stereo Network using Global Lighting Contextscited by 18
  11. 2023MVPSNet: Fast Generalizable Multi-view Photometric Stereocited by 18
  12. 2023SuperNormal: Neural Surface Reconstruction via Multi-View Normal Integrationcited by 18
35 more
  1. 2022Self-calibrating Photometric Stereo by Neural Inverse Renderingcited by 17
  2. 2022Multi-View Photometric Stereo Revisitedcited by 17
  3. 2022ShadowNeuS: Neural SDF Reconstruction by Shadow Ray Supervisioncited by 17
  4. 2023Multi-View Azimuth Stereo via Tangent Space Consistencycited by 16
  5. 2022PS-Transformer: Learning Sparse Photometric Stereo Network using Self-Attention Mechanismcited by 13
  6. 2022Fast Light-Weight Near-Field Photometric Stereocited by 12
  7. 2022A CNN Based Approach for the Point-Light Photometric Stereo Problemcited by 10
  8. 2022Deep Learning Methods for Calibrated Photometric Stereo and Beyondcited by 10
  9. 2025Diffusion Knows Transparency: Repurposing Video Diffusion for Transparent Object Depth and Normal Estimationcited by 9
  10. 2025Light of Normals: Unified Feature Representation for Universal Photometric Stereocited by 8
  11. 2021Neural Architecture Search for Efficient Uncalibrated Deep Photometric Stereocited by 7
  12. 2022DeepShadow: Neural Shape from Shadowcited by 6
  13. 2022DeepPS2: Revisiting Photometric Stereo Using Two Differently Illuminated Imagescited by 5
  14. 2023DANI-Net: Uncalibrated Photometric Stereo by Differentiable Shadow Handling, Anisotropic Reflectance Modeling, and Neural Inverse Renderingcited by 5
  15. 2024Sparse Views, Near Light: A Practical Paradigm for Uncalibrated Point-light Photometric Stereocited by 5
  16. 2025Multi-view Surface Reconstruction Using Normal and Reflectance Cuescited by 5
  17. 2021Incorporating Lambertian Priors into Surface Normals Measurementcited by 4
  18. 2024NPLMV-PS: Neural Point-Light Multi-View Photometric Stereocited by 4
  19. 2024Physics-Free Spectrally Multiplexed Photometric Stereo under Unknown Spectral Compositioncited by 4
  20. 2022MS-PS: A Multi-Scale Network for Photometric Stereo With a New Comprehensive Training Datasetcited by 3
  21. 2023A Neural Height-Map Approach for the Binocular Photometric Stereo Problemcited by 3
  22. 2024LUCES-MV: A Multi-View Dataset for Near-Field Point Light Source Photometric Stereocited by 2
  23. 2025Mobile Robotic Multi-View Photometric Stereocited by 1
  24. 2025PS-GS: Gaussian Splatting for Multi-View Photometric Stereocited by 1
  25. 2025Endoscopic Depth Estimation Based on Deep Learning: A Surveycited by 1
  26. 2025Geometry Meets Light: Leveraging Geometric Priors for Universal Photometric Stereo under Limited Multi-Illumination Cuescited by 1
  27. 2022Deep Uncalibrated Photometric Stereo via Inter-Intra Image Feature Fusioncited by 0
  28. 2022NeIF: Representing General Reflectance as Neural Intrinsics Fields for Uncalibrated Photometric Stereocited by 0
  29. 2022NeuralMPS: Non-Lambertian Multispectral Photometric Stereo via Spectral Reflectance Decompositioncited by 0
  30. 2024LIPIDS: Learning-based Illumination Planning In Discretized (Light) Space for Photometric Stereocited by 0
  31. 2024Incorporating dense metric depth into neural 3D representations for view synthesis and relightingcited by 0
  32. 2025PS-EIP: Robust Photometric Stereo Based on Event Interval Profilecited by 0
  33. 2025THIRDEYE: Cue-Aware Monocular Depth Estimation via Brain-Inspired Multi-Stage Fusioncited by 0
  34. 2025Neural Multi-View Self-Calibrated Photometric Stereo without Photometric Stereo Cuescited by 0
  35. 2026Calibration-Free Surface Normals Estimation in Vision-Based Tactile Sensing using Universal Photometric Stereocited by 0