# LumiGAN: Unconditional Generation of Relightable 3D Human Faces

arXiv: https://arxiv.org/abs/2304.13153 · HTML: https://mlsanity.com/paper/2304.13153/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 48 of its 77 references that are in the map.
- First posted on arXiv 25 Apr 2023.

## Builds on (most cited first, 30 of 48)

- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [Efficient Geometry-aware 3D Generative Adversarial Networks](https://mlsanity.com/paper/2112.07945/) (2021)
- [GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields](https://mlsanity.com/paper/2011.12100/) (2020)
- [pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis](https://mlsanity.com/paper/2012.00926/) (2020)
- [GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis](https://mlsanity.com/paper/2007.02442/) (2020)
- [Which Training Methods for GANs do actually Converge?](https://mlsanity.com/paper/1801.04406/) (2018)
- [Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fields](https://mlsanity.com/paper/2112.03907/) (2021)
- [How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)](https://mlsanity.com/paper/1703.07332/) (2017)
- [NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesis](https://mlsanity.com/paper/2012.03927/) (2020)
- [StyleNeRF: A Style-based 3D-Aware Generator for High-resolution Image Synthesis](https://mlsanity.com/paper/2110.08985/) (2021)
- [NeRD: Neural Reflectance Decomposition from Image Collections](https://mlsanity.com/paper/2012.03918/) (2020)
- [Advances in Neural Rendering](https://mlsanity.com/paper/2111.05849/) (2021)
- [PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relighting](https://mlsanity.com/paper/2104.00674/) (2021)
- [StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generation](https://mlsanity.com/paper/2112.11427/) (2021)
- [HeadNeRF: A Real-time NeRF-based Parametric Head Model](https://mlsanity.com/paper/2112.05637/) (2021)
- [GRAM: Generative Radiance Manifolds for 3D-Aware Image Generation](https://mlsanity.com/paper/2112.08867/) (2021)
- [Neural Head Avatars from Monocular RGB Videos](https://mlsanity.com/paper/2112.01554/) (2021)
- [Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decomposition](https://mlsanity.com/paper/2110.14373/) (2021)
- [Single Image Portrait Relighting](https://mlsanity.com/paper/1905.00824/) (2019)
- [CIPS-3D: A 3D-Aware Generator of GANs Based on Conditionally-Independent Pixel Synthesis](https://mlsanity.com/paper/2110.09788/) (2021)
- [Robust High-Resolution Video Matting with Temporal Guidance](https://mlsanity.com/paper/2108.11515/) (2021)
- [MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decomposition](https://mlsanity.com/paper/2011.11961/) (2020)
- [3D-aware Image Synthesis via Learning Structural and Textural Representations](https://mlsanity.com/paper/2112.10759/) (2021)
- [EpiGRAF: Rethinking training of 3D GANs](https://mlsanity.com/paper/2206.10535/) (2022)
- [Generative Neural Articulated Radiance Fields](https://mlsanity.com/paper/2206.14314/) (2022)
- [GIRAFFE HD: A High-Resolution 3D-aware Generative Model](https://mlsanity.com/paper/2203.14954/) (2022)

## Built on by (most cited first, 14 of 14)

- [State of the Art on Diffusion Models for Visual Computing](https://mlsanity.com/paper/2310.07204/) (2023)
- [Relightable Gaussian Codec Avatars](https://mlsanity.com/paper/2312.03704/) (2023)
- [URAvatar: Universal Relightable Gaussian Codec Avatars](https://mlsanity.com/paper/2410.24223/) (2024)
- [Holo-Relighting: Controllable Volumetric Portrait Relighting from a Single Image](https://mlsanity.com/paper/2403.09632/) (2024)
- [Lite2Relight: 3D-aware Single Image Portrait Relighting](https://mlsanity.com/paper/2407.10487/) (2024)
- [GenLit: Reformulating Single-Image Relighting as Video Generation](https://mlsanity.com/paper/2412.11224/) (2024)
- [Relightable Neural Actor with Intrinsic Decomposition and Pose Control](https://mlsanity.com/paper/2312.11587/) (2023)
- [3DPR: Single Image 3D Portrait Relight using Generative Priors](https://mlsanity.com/paper/2510.15846/) (2025)
- [Articulated 3D Head Avatar Generation using Text-to-Image Diffusion Models](https://mlsanity.com/paper/2307.04859/) (2023)
- [Total-Editing: Head Avatar with Editable Appearance, Motion, and Lighting](https://mlsanity.com/paper/2505.20582/) (2025)
- [Analyzing and Improving the Skin Tone Consistency and Bias in Implicit 3D Relightable Face Generators](https://mlsanity.com/paper/2411.12002/) (2024)
- [HeadLighter: Disentangling Illumination in Generative 3D Gaussian Heads via Lightstage Captures](https://mlsanity.com/paper/2601.02103/) (2026)
- [RelightAnyone: A Generalized Relightable 3D Gaussian Head Model](https://mlsanity.com/paper/2601.03357/) (2026)
- [Dual Diffusion Models for Multi-modal Guided 3D Avatar Generation](https://mlsanity.com/paper/2603.04307/) (2026)

## Abstract (arXiv)

Unsupervised learning of 3D human faces from unstructured 2D image data is an active research area. While recent works have achieved an impressive level of photorealism, they commonly lack control of lighting, which prevents the generated assets from being deployed in novel environments. To this end, we introduce LumiGAN, an unconditional Generative Adversarial Network (GAN) for 3D human faces with a physically based lighting module that enables relighting under novel illumination at inference time. Unlike prior work, LumiGAN can create realistic shadow effects using an efficient visibility formulation that is learned in a self-supervised manner. LumiGAN generates plausible physical properties for relightable faces, including surface normals, diffuse albedo, and specular tint without any ground truth data. In addition to relightability, we demonstrate significantly improved geometry generation compared to state-of-the-art non-relightable 3D GANs and notably better photorealism than existing relightable GANs.