mlsanityData to 7 Oct 2026

Learning Physics-guided Face Relighting under Directional Light

arXiv 1906.03355 ↗First posted 7 Jun 2019cs.CV cs.GR cs.LGcited by 90

Not on the map. Why?

Abstract (arXiv)

Relighting is an essential step in realistically transferring objects from a captured image into another environment. For example, authentic telepresence in Augmented Reality requires faces to be displayed and relit consistent with the observer's scene lighting. We investigate end-to-end deep learning architectures that both de-light and relight an image of a human face. Our model decomposes the input image into intrinsic components according to a diffuse physics-based image formation model. We enable non-diffuse effects including cast shadows and specular highlights by predicting a residual correction to the diffuse render. To train and evaluate our model, we collected a portrait database of 21 subjects with various expressions and poses. Each sample is captured in a controlled light stage setup with 32 individual light sources. Our method creates precise and believable relighting results and generalizes to complex illumination conditions and challenging poses, including when the subject is not looking straight at the camera.

Key facts. Cited by 90 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 15; 2022: 17; 2023: 11; 2024: 24; 2025: 15; 2026: 8.

90 papers.

Sort:

By area:

  1. 2023NeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview Imagescited by 163
  2. 2024DiLightNet: Fine-grained Lighting Control for Diffusion-based Image Generationcited by 93
  3. 2024Neural Gaffer: Relighting Any Object via Diffusioncited by 91
  4. 2023DiffusionRig: Learning Personalized Priors for Facial Appearance Editingcited by 74
  5. 2022Learning to Relight Portrait Images via a Virtual Light Stage and Synthetic-to-Real Adaptationcited by 67
  6. 2024SwitchLight: Co-design of Physics-driven Architecture and Pre-training Framework for Human Portrait Relightingcited by 66
  7. 2021Making Images Real Again: A Comprehensive Survey on Deep Image Compositioncited by 63
  8. 2023Relightful Harmonization: Lighting-aware Portrait Background Replacementcited by 56
  9. 2021Neural Video Portrait Relighting in Real-time via Consistency Modelingcited by 46
  10. 2022Face Relighting with Geometrically Consistent Shadowscited by 43
  11. 2021Towards High Fidelity Face Relighting with Realistic Shadowscited by 42
  12. 2023ReLight My NeRF: A Dataset for Novel View Synthesis and Relighting of Real World Objectscited by 42
38 more
  1. 2021NeLF: Neural Light-transport Field for Portrait View Synthesis and Relightingcited by 38
  2. 2021A Survey on Intrinsic Images: Delving Deep Into Lambert and Beyondcited by 37
  3. 2022VoLux-GAN: A Generative Model for 3D Face Synthesis with HDRI Relightingcited by 37
  4. 2024LumiNet: Latent Intrinsics Meets Diffusion Models for Indoor Scene Relightingcited by 37
  5. 2025LBM: Latent Bridge Matching for Fast Image-to-Image Translationcited by 36
  6. 2025LightLab: Controlling Light Sources in Images with Diffusion Modelscited by 36
  7. 2022Geometry-aware Single-image Full-body Human Relightingcited by 34
  8. 2024Holo-Relighting: Controllable Volumetric Portrait Relighting from a Single Imagecited by 32
  9. 2022De-rendering 3D Objects in the Wildcited by 31
  10. 2021Single-image Full-body Human Relightingcited by 30
  11. 2022SunStage: Portrait Reconstruction and Relighting using the Sun as a Light Stagecited by 30
  12. 2022OutCast: Outdoor Single-image Relighting with Cast Shadowscited by 30
  13. 2024Lite2Relight: 3D-aware Single Image Portrait Relightingcited by 25
  14. 2025VidCRAFT3: Camera, Object, and Lighting Control for Image-to-Video Generationcited by 25
  15. 2025SynthLight: Portrait Relighting with Diffusion Model by Learning to Re-render Synthetic Facescited by 24
  16. 2022Multi-view Inverse Rendering for Large-scale Real-world Indoor Scenescited by 23
  17. 2024ScribbleLight: Single Image Indoor Relighting with Scribblescited by 22
  18. 2021A Light Stage on Every Deskcited by 21
  19. 2023RelightableHands: Efficient Neural Relighting of Articulated Hand Modelscited by 21
  20. 2024OmniSR: Shadow Removal under Direct and Indirect Lightingcited by 19
  21. 2024URHand: Universal Relightable Handscited by 17
  22. 2024Latent Intrinsics Emerge from Training to Relightcited by 17
  23. 2025IntrinsicEdit: Precise generative image manipulation in intrinsic spacecited by 17
  24. 2022SIMBAR: Single Image-Based Scene Relighting For Effective Data Augmentation For Automated Driving Vision Taskscited by 15
  25. 2023DiFaReli++: Diffusion Face Relighting with Consistent Cast Shadowscited by 14
  26. 2021High-fidelity Face Tracking for AR/VR via Deep Lighting Adaptationcited by 13
  27. 2024Detail-Preserving Latent Diffusion for Stable Shadow Removalcited by 13
  28. 2023ReliTalk: Relightable Talking Portrait Generation from a Single Videocited by 12
  29. 2023Controllable Light Diffusion for Portraitscited by 11
  30. 2025TC-Light: Temporally Coherent Generative Rendering for Realistic World Transfercited by 11
  31. 2024Generative Portrait Shadow Removalcited by 10
  32. 2025High-Fidelity Relightable Monocular Portrait Animation with Lighting-Controllable Video Diffusion Modelcited by 8
  33. 2025DreamLight: Towards Harmonious and Consistent Image Relightingcited by 8
  34. 20253DPR: Single Image 3D Portrait Relight using Generative Priorscited by 8
  35. 2023Personalized Video Relighting With an At-Home Light Stagecited by 7
  36. 2024Text2Relight: Creative Portrait Relighting with Text Guidancecited by 7
  37. 2024COMPOSE: Comprehensive Portrait Shadow Editingcited by 6
  38. 2024Relighting from a Single Image: Datasets and Deep Intrinsic-based Architecturecited by 6

50 most cited of 90 All 90 (JSON)