mlsanityData to 14 Oct 2026

SfSNet: Learning Shape, Reflectance and Illuminance of Faces in the Wild

arXiv 1712.01261 ↗First posted 2 Dec 2017cs.CVcited by 110

Not on the map. Why?

Abstract (arXiv)

We present SfSNet, an end-to-end learning framework for producing an accurate decomposition of an unconstrained human face image into shape, reflectance and illuminance. SfSNet is designed to reflect a physical lambertian rendering model. SfSNet learns from a mixture of labeled synthetic and unlabeled real world images. This allows the network to capture low frequency variations from synthetic and high frequency details from real images through the photometric reconstruction loss. SfSNet consists of a new decomposition architecture with residual blocks that learns a complete separation of albedo and normal. This is used along with the original image to predict lighting. SfSNet produces significantly better quantitative and qualitative results than state-of-the-art methods for inverse rendering and independent normal and illumination estimation.

Key facts. Cited by 110 papers in the map (data through 14 Oct 2026). First posted on arXiv 2 Dec 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 38; 2022: 25; 2023: 18; 2024: 15; 2025: 9; 2026: 5.

110 papers.

Sort:

By area:

  1. 2023DiffusionRig: Learning Personalized Priors for Facial Appearance Editingcited by 75
  2. 2022Learning to Relight Portrait Images via a Virtual Light Stage and Synthetic-to-Real Adaptationcited by 67
  3. 2024SwitchLight: Co-design of Physics-driven Architecture and Pre-training Framework for Human Portrait Relightingcited by 67
  4. 2021AvatarMe++: Facial Shape and BRDF Inference with Photorealistic Rendering-Aware GANscited by 49
  5. 2021Towards High Fidelity Monocular Face Reconstruction with Rich Reflectance using Self-supervised Learning and Ray Tracingcited by 48
  6. 2021Neural Video Portrait Relighting in Real-time via Consistency Modelingcited by 46
  7. 2022Face Relighting with Geometrically Consistent Shadowscited by 43
  8. 2021Towards High Fidelity Face Relighting with Realistic Shadowscited by 42
  9. 2021NeLF: Neural Light-transport Field for Portrait View Synthesis and Relightingcited by 38
  10. 2023FitMe: Deep Photorealistic 3D Morphable Model Avatarscited by 38
  11. 2021A Survey on Intrinsic Images: Delving Deep Into Lambert and Beyondcited by 37
  12. 2024A Diffusion Approach to Radiance Field Relighting using Multi-Illumination Synthesiscited by 37
38 more
  1. 2021Shape and Material Capture at Homecited by 36
  2. 2021FaceScape: 3D Facial Dataset and Benchmark for Single-View 3D Face Reconstructioncited by 36
  3. 2021Practical Face Reconstruction via Differentiable Ray Tracingcited by 35
  4. 2024DifFRelight: Diffusion-Based Facial Performance Relightingcited by 35
  5. 2022Geometry-aware Single-image Full-body Human Relightingcited by 34
  6. 2022Towards Racially Unbiased Skin Tone Estimation via Scene Disambiguationcited by 32
  7. 2021Riggable 3D Face Reconstruction via In-Network Optimizationcited by 31
  8. 2022De-rendering 3D Objects in the Wildcited by 31
  9. 2021Single-image Full-body Human Relightingcited by 30
  10. 2022SunStage: Portrait Reconstruction and Relighting using the Sun as a Light Stagecited by 30
  11. 2021De-rendering the World's Revolutionary Artefactscited by 28
  12. 2022Facial Geometric Detail Recovery via Implicit Representationcited by 27
  13. 2021Unsupervised Human Pose Estimation through Transforming Shape Templatescited by 26
  14. 2023NeISF: Neural Incident Stokes Field for Geometry and Material Estimationcited by 25
  15. 2025VidCRAFT3: Camera, Object, and Lighting Control for Image-to-Video Generationcited by 25
  16. 2025SynthLight: Portrait Relighting with Diffusion Model by Learning to Re-render Synthetic Facescited by 24
  17. 2022Physical-World Optical Adversarial Attacks on 3D Face Recognitioncited by 23
  18. 2022PhotoScene: Photorealistic Material and Lighting Transfer for Indoor Scenescited by 22
  19. 2021High Resolution Face Editing with Masked GAN Latent Code Optimizationcited by 21
  20. 2021A Light Stage on Every Deskcited by 21
  21. 2023RelightableHands: Efficient Neural Relighting of Articulated Hand Modelscited by 21
  22. 2021Outdoor inverse rendering from a single image using multiview self-supervisioncited by 18
  23. 2023MVPSNet: Fast Generalizable Multi-view Photometric Stereocited by 18
  24. 2021Inverting Generative Adversarial Renderer for Face Reconstructioncited by 17
  25. 2021Self-Supervised 3D Face Reconstruction via Conditional Estimationcited by 17
  26. 2022S2F2: Self-Supervised High Fidelity Face Reconstruction from Monocular Imagecited by 17
  27. 20223D-FM GAN: Towards 3D-Controllable Face Manipulationcited by 17
  28. 2024URHand: Universal Relightable Handscited by 17
  29. 2021Learning to Aggregate and Personalize 3D Face from In-the-Wild Photo Collectioncited by 16
  30. 2021Detailed Avatar Recovery from Single Imagecited by 16
  31. 2021Adversarial Relighting Against Face Recognitioncited by 16
  32. 2023Weakly-supervised Single-view Image Relightingcited by 14
  33. 2023DiFaReli++: Diffusion Face Relighting with Consistent Cast Shadowscited by 14
  34. 2021High-fidelity Face Tracking for AR/VR via Deep Lighting Adaptationcited by 13
  35. 2022Rotation-Equivariant Conditional Spherical Neural Fields for Learning a Natural Illumination Priorcited by 12
  36. 2025Light-X: Generative 4D Video Rendering with Camera and Illumination Controlcited by 12
  37. 2021Facial Depth and Normal Estimation using Single Dual-Pixel Cameracited by 11
  38. 2023Learning Visibility Field for Detailed 3D Human Reconstruction and Relightingcited by 11

50 most cited of 110 All 110 (JSON)