# Relightable Gaussian Codec Avatars

arXiv: https://arxiv.org/abs/2312.03704 · HTML: https://mlsanity.com/paper/2312.03704/

## Key facts

- Cited by 127 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 99 references that are in the map.
- First posted on arXiv 6 Dec 2023.

## Builds on (most cited first, 30 of 35)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [4D Gaussian Splatting for Real-Time Dynamic Scene Rendering](https://mlsanity.com/paper/2310.08528/) (2023)
- [Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis](https://mlsanity.com/paper/2308.09713/) (2023)
- [Image2StyleGAN: How to Embed Images Into the StyleGAN Latent Space?](https://mlsanity.com/paper/1904.03189/) (2019)
- [Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks](https://mlsanity.com/paper/1602.07868/) (2016)
- [Extracting Triangular 3D Models, Materials, and Lighting From Images](https://mlsanity.com/paper/2111.12503/) (2021)
- [PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relighting](https://mlsanity.com/paper/2104.00674/) (2021)
- [Mixture of Volumetric Primitives for Efficient Neural Rendering](https://mlsanity.com/paper/2103.01954/) (2021)
- [StyleRig: Rigging StyleGAN for 3D Control over Portrait Images](https://mlsanity.com/paper/2004.00121/) (2020)
- [NeRSemble: Multi-view Radiance Field Reconstruction of Human Heads](https://mlsanity.com/paper/2305.03027/) (2023)
- [Point-Based Neural Rendering with Per-View Optimization](https://mlsanity.com/paper/2109.02369/) (2021)
- [PointAvatar: Deformable Point-based Head Avatars from Videos](https://mlsanity.com/paper/2212.08377/) (2022)
- [Deep Appearance Models for Face Rendering](https://mlsanity.com/paper/1808.00362/) (2018)
- [Instant Volumetric Head Avatars](https://mlsanity.com/paper/2211.12499/) (2022)
- [Single Image Portrait Relighting](https://mlsanity.com/paper/1905.00824/) (2019)
- [Pixel Codec Avatars](https://mlsanity.com/paper/2104.04638/) (2021)
- [Deep Reflectance Volumes: Relightable Reconstructions from Multi-View Photometric Images](https://mlsanity.com/paper/2007.09892/) (2020)
- [Learning Formation of Physically-Based Face Attributes](https://mlsanity.com/paper/2004.03458/) (2020)
- [AvatarMe: Realistically Renderable 3D Facial Reconstruction "in-the-wild"](https://mlsanity.com/paper/2003.13845/) (2020)
- [Neural Point Catacaustics for Novel-View Synthesis of Reflections](https://mlsanity.com/paper/2301.01087/) (2023)
- [Neural Light Transport for Relighting and View Synthesis](https://mlsanity.com/paper/2008.03806/) (2020)
- [Learning to Relight Portrait Images via a Virtual Light Stage and Synthetic-to-Real Adaptation](https://mlsanity.com/paper/2209.10510/) (2022)
- [LatentAvatar: Learning Latent Expression Code for Expressive Neural Head Avatar](https://mlsanity.com/paper/2305.01190/) (2023)
- [AvatarMe++: Facial Shape and BRDF Inference with Photorealistic Rendering-Aware GANs](https://mlsanity.com/paper/2112.05957/) (2021)
- [HAvatar: High-fidelity Head Avatar via Facial Model Conditioned Neural Radiance Field](https://mlsanity.com/paper/2309.17128/) (2023)
- [VolTeMorph: Realtime, Controllable and Generalisable Animation of Volumetric Representations](https://mlsanity.com/paper/2208.00949/) (2022)
- [Relightify: Relightable 3D Faces from a Single Image via Diffusion Models](https://mlsanity.com/paper/2305.06077/) (2023)
- [Instant Multi-View Head Capture through Learnable Registration](https://mlsanity.com/paper/2306.07437/) (2023)
- [Towards Practical Capture of High-Fidelity Relightable Avatars](https://mlsanity.com/paper/2309.04247/) (2023)

## Built on by (most cited first, 30 of 127)

- [GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation](https://mlsanity.com/paper/2403.14621/) (2024)
- [Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussians](https://mlsanity.com/paper/2403.17898/) (2024)
- [A Survey on 3D Gaussian Splatting](https://mlsanity.com/paper/2401.03890/) (2024)
- [Recent Advances in 3D Gaussian Splatting](https://mlsanity.com/paper/2403.11134/) (2024)
- [Revising Densification in Gaussian Splatting](https://mlsanity.com/paper/2404.06109/) (2024)
- [3D Gaussian Splatting: Survey, Technologies, Challenges, and Opportunities](https://mlsanity.com/paper/2407.17418/) (2024)
- [Spec-Gaussian: Anisotropic View-Dependent Appearance for 3D Gaussian Splatting](https://mlsanity.com/paper/2402.15870/) (2024)
- [Analytic-Splatting: Anti-Aliased 3D Gaussian Splatting via Analytic Integration](https://mlsanity.com/paper/2403.11056/) (2024)
- [Avat3r: Large Animatable Gaussian Reconstruction Model for High-fidelity 3D Head Avatars](https://mlsanity.com/paper/2502.20220/) (2025)
- [SplatFields: Neural Gaussian Splats for Sparse 3D and 4D Reconstruction](https://mlsanity.com/paper/2409.11211/) (2024)
- [CAP4D: Creating Animatable 4D Portrait Avatars with Morphable Multi-View Diffusion Models](https://mlsanity.com/paper/2412.12093/) (2024)
- [SWinGS: Sliding Windows for Dynamic 3D Gaussian Splatting](https://mlsanity.com/paper/2312.13308/) (2023)
- [MeGA: Hybrid Mesh-Gaussian Head Avatar for High-Fidelity Rendering and Head Editing](https://mlsanity.com/paper/2404.19026/) (2024)
- [Human Hair Reconstruction with Strand-Aligned 3D Gaussians](https://mlsanity.com/paper/2409.14778/) (2024)
- [GAF: Gaussian Avatar Reconstruction from Monocular Videos via Multi-view Diffusion](https://mlsanity.com/paper/2412.10209/) (2024)
- [FATE: Full-head Gaussian Avatar with Textural Editing from Monocular Video](https://mlsanity.com/paper/2411.15604/) (2024)
- [HAHA: Highly Articulated Gaussian Human Avatars with Textured Mesh Prior](https://mlsanity.com/paper/2404.01053/) (2024)
- [Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Prior](https://mlsanity.com/paper/2503.01610/) (2025)
- [GauStudio: A Modular Framework for 3D Gaussian Splatting and Beyond](https://mlsanity.com/paper/2403.19632/) (2024)
- [HRAvatar: High-Quality and Relightable Gaussian Head Avatar](https://mlsanity.com/paper/2503.08224/) (2025)
- [GVA: Reconstructing Vivid 3D Gaussian Avatars from Monocular Videos](https://mlsanity.com/paper/2402.16607/) (2024)
- [FaceLift: Learning Generalizable Single Image 3D Face Reconstruction from Synthetic Heads](https://mlsanity.com/paper/2412.17812/) (2024)
- [GUAVA: Generalizable Upper Body 3D Gaussian Avatar](https://mlsanity.com/paper/2505.03351/) (2025)
- [Gaussian Eigen Models for Human Heads](https://mlsanity.com/paper/2407.04545/) (2024)
- [LumiGauss: Relightable Gaussian Splatting in the Wild](https://mlsanity.com/paper/2408.04474/) (2024)
- [IntrinsicAvatar: Physically Based Inverse Rendering of Dynamic Humans from Monocular Videos via Explicit Ray Tracing](https://mlsanity.com/paper/2312.05210/) (2023)
- [Advancing Extended Reality with 3D Gaussian Splatting: Innovations and Prospects](https://mlsanity.com/paper/2412.06257/) (2024)
- [Tri2-plane: Thinking Head Avatar via Feature Pyramid](https://mlsanity.com/paper/2401.09386/) (2024)
- [DiffLocks: Generating 3D Hair from a Single Image using Diffusion Models](https://mlsanity.com/paper/2505.06166/) (2025)
- [SurFhead: Affine Rig Blending for Geometrically Accurate 2D Gaussian Surfel Head Avatars](https://mlsanity.com/paper/2410.11682/) (2024)

## Abstract (arXiv)

The fidelity of relighting is bounded by both geometry and appearance representations. For geometry, both mesh and volumetric approaches have difficulty modeling intricate structures like 3D hair geometry. For appearance, existing relighting models are limited in fidelity and often too slow to render in real-time with high-resolution continuous environments. In this work, we present Relightable Gaussian Codec Avatars, a method to build high-fidelity relightable head avatars that can be animated to generate novel expressions. Our geometry model based on 3D Gaussians can capture 3D-consistent sub-millimeter details such as hair strands and pores on dynamic face sequences. To support diverse materials of human heads such as the eyes, skin, and hair in a unified manner, we present a novel relightable appearance model based on learnable radiance transfer. Together with global illumination-aware spherical harmonics for the diffuse components, we achieve real-time relighting with all-frequency reflections using spherical Gaussians. This appearance model can be efficiently relit under both point light and continuous illumination. We further improve the fidelity of eye reflections and enable explicit gaze control by introducing relightable explicit eye models. Our method outperforms existing approaches without compromising real-time performance. We also demonstrate real-time relighting of avatars on a tethered consumer VR headset, showcasing the efficiency and fidelity of our avatars.