mlsanityData to 7 Oct 2026

FaceLit: Neural 3D Relightable Faces

arXiv 2303.15437 ↗First posted 27 Mar 2023cs.CVcited by 20

Not on the map. Why?

Abstract (arXiv)

We propose a generative framework, FaceLit, capable of generating a 3D face that can be rendered at various user-defined lighting conditions and views, learned purely from 2D images in-the-wild without any manual annotation. Unlike existing works that require careful capture setup or human labor, we rely on off-the-shelf pose and illumination estimators. With these estimates, we incorporate the Phong reflectance model in the neural volume rendering framework. Our model learns to generate shape and material properties of a face such that, when rendered according to the natural statistics of pose and illumination, produces photorealistic face images with multiview 3D and illumination consistency. Our method enables photorealistic generation of faces with explicit illumination and view controls on multiple datasets - FFHQ, MetFaces and CelebA-HQ. We show state-of-the-art photorealism among 3D aware GANs on FFHQ dataset achieving an FID score of 3.5.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 26 of its 41 references that are in the map. First posted on arXiv 27 Mar 2023.

Builds on

26 of 41 references.

References · 26

  1. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  2. 2022Generative Adversarial Networkscited by 5,603
  3. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  4. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  5. 2018Demystifying MMD GANscited by 1,268
  6. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,204
  7. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  8. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  9. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 784
  10. 2020pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesiscited by 708
  11. 2021Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fieldscited by 569
  12. 2019Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Setcited by 481
14 more
  1. 2021StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesiscited by 477
  2. 2020Learning an Animatable Detailed 3D Face Model from In-The-Wild Imagescited by 475
  3. 2020NeRD: Neural Reflectance Decomposition from Image Collectionscited by 446
  4. 2021Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decompositioncited by 204
  5. 2021NeRFactor: Neural Factorization of Shape and Reflectance Under an Unknown Illuminationcited by 135
  6. 2022VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Gridscited by 133
  7. 2022SAMURAI: Shape And Material from Unconstrained Real-world Arbitrary Image collectionscited by 89
  8. 2021LOLNeRF: Learn from One Lookcited by 84
  9. 2021A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesiscited by 72
  10. 2020Lifting 2D StyleGAN for 3D-Aware Face Generationcited by 64
  11. 2022Generative Multiplane Images: Making a 2D GAN 3D-Awarecited by 57
  12. 2020GIF: Generative Interpretable Facescited by 53
  13. 2022VoLux-GAN: A Generative Model for 3D Face Synthesis with HDRI Relightingcited by 37
  14. 2020MorphGAN: One-Shot Face Synthesis GAN for Detecting Recognition Biascited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 8; 2024: 7; 2025: 2; 2026: 3.

20 papers.

Sort:

By area:

  1. 2023HUGS: Human Gaussian Splatscited by 154
  2. 2023Relightable Gaussian Codec Avatarscited by 126
  3. 2024Neural Gaffer: Relighting Any Object via Diffusioncited by 91
  4. 2023Stanford-ORB: A Real-World 3D Object Inverse Rendering Benchmarkcited by 51
  5. 2023MonoNPHM: Dynamic Head Reconstruction from Monocular Videoscited by 35
  6. 2024Holo-Relighting: Controllable Volumetric Portrait Relighting from a Single Imagecited by 32
  7. 2023AvatarStudio: Text-driven Editing of 3D Dynamic Human Head Avatarscited by 29
  8. 2025Lux Post Facto: Learning Portrait Performance Relighting with Conditional Video Diffusion and a Hybrid Datasetcited by 28
  9. 2024Real-time 3D-aware Portrait Video Relightingcited by 21
  10. 2024GenLit: Reformulating Single-Image Relighting as Video Generationcited by 20
  11. 2023DiFaReli++: Diffusion Face Relighting with Consistent Cast Shadowscited by 14
  12. 2023LumiGAN: Unconditional Generation of Relightable 3D Human Facescited by 14
8 more
  1. 2024Gaussian Shadow Casting for Neural Characterscited by 14
  2. 2023Relightable Neural Actor with Intrinsic Decomposition and Pose Controlcited by 11
  3. 2024COMPOSE: Comprehensive Portrait Shadow Editingcited by 6
  4. 2025Total-Editing: Head Avatar with Editable Appearance, Motion, and Lightingcited by 2
  5. 2024Analyzing and Improving the Skin Tone Consistency and Bias in Implicit 3D Relightable Face Generatorscited by 1
  6. 2026HeadLighter: Disentangling Illumination in Generative 3D Gaussian Heads via Lightstage Capturescited by 0
  7. 2026RelightAnyone: A Generalized Relightable 3D Gaussian Head Modelcited by 0
  8. 2026Dual Diffusion Models for Multi-modal Guided 3D Avatar Generationcited by 0