# Generative Relightable Avatars

arXiv: https://arxiv.org/abs/2606.22718 · HTML: https://mlsanity.com/paper/2606.22718/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 40 of its 49 references that are in the map.
- First posted on arXiv 21 Jun 2026.

## Builds on (most cited first, 30 of 40)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Structured 3D Latents for Scalable and Versatile 3D Generation](https://mlsanity.com/paper/2412.01506/) (2024)
- [VACE: All-in-One Video Creation and Editing](https://mlsanity.com/paper/2503.07598/) (2025)
- [Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation](https://mlsanity.com/paper/2501.12202/) (2025)
- [NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstruction](https://mlsanity.com/paper/2212.05231/) (2022)
- [Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision](https://mlsanity.com/paper/1905.06817/) (2019)
- [Native and Compact Structured Latents for 3D Generation](https://mlsanity.com/paper/2512.14692/) (2025)
- [Learning to Predict Indoor Illumination from a Single Image](https://mlsanity.com/paper/1704.00090/) (2017)
- [RGBleftrightarrowX: Image decomposition and synthesis using material- and lighting-aware diffusion models](https://mlsanity.com/paper/2405.00666/) (2024)
- [Real-time Deep Dynamic Characters](https://mlsanity.com/paper/2105.01794/) (2021)
- [Neural Gaffer: Relighting Any Object via Diffusion](https://mlsanity.com/paper/2406.07520/) (2024)
- [Stable Video Infinity: Infinite-Length Video Generation with Error Recycling](https://mlsanity.com/paper/2510.09212/) (2025)
- [SwitchLight: Co-design of Physics-driven Architecture and Pre-training Framework for Human Portrait Relighting](https://mlsanity.com/paper/2402.18848/) (2024)
- [Fr'echet Video Motion Distance: A Metric for Evaluating Motion Consistency in Videos](https://mlsanity.com/paper/2407.16124/) (2024)
- [Relightful Harmonization: Lighting-aware Portrait Background Replacement](https://mlsanity.com/paper/2312.06886/) (2023)
- [DiffusionRenderer: Neural Inverse and Forward Rendering with Video Diffusion Models](https://mlsanity.com/paper/2501.18590/) (2025)
- [Relighting4D: Neural Relightable Human from Videos](https://mlsanity.com/paper/2207.07104/) (2022)
- [DifFRelight: Diffusion-Based Facial Performance Relighting](https://mlsanity.com/paper/2410.08188/) (2024)
- [MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videos](https://mlsanity.com/paper/2407.08414/) (2024)
- [Holo-Relighting: Controllable Volumetric Portrait Relighting from a Single Image](https://mlsanity.com/paper/2403.09632/) (2024)
- [Relightable and Animatable Neural Avatar from Sparse-View Video](https://mlsanity.com/paper/2308.07903/) (2023)
- [Lux Post Facto: Learning Portrait Performance Relighting with Conditional Video Diffusion and a Hybrid Dataset](https://mlsanity.com/paper/2503.14485/) (2025)
- [Blind Video Deflickering by Neural Filtering with a Flawed Atlas](https://mlsanity.com/paper/2303.08120/) (2023)
- [SynthLight: Portrait Relighting with Diffusion Model by Learning to Re-render Synthetic Faces](https://mlsanity.com/paper/2501.09756/) (2025)
- [Relightable Full-Body Gaussian Codec Avatars](https://mlsanity.com/paper/2501.14726/) (2025)
- [IntrinsicAvatar: Physically Based Inverse Rendering of Dynamic Humans from Monocular Videos via Explicit Ray Tracing](https://mlsanity.com/paper/2312.05210/) (2023)
- [RANA: Relightable Articulated Neural Avatars](https://mlsanity.com/paper/2212.03237/) (2022)

## Abstract (arXiv)

We present Generative Relightable Avatars (GRA), a person-specific method for photorealistic free-view rendering and environment-map relighting of full-body humans. We postulate that modeling fine-grained appearance details is inherently a one-to-many problem that can benefit from a generative formulation. In contrast to fully regressive relightable avatar methods, GRA follows a hybrid approach that combines controllable, physics-grounded relighting with probabilistic refinement. Starting from a tracked animated mesh, we optimize material parameters in UV-space and render a coarse relit appearance under a target HDR environment map. Next, we refine the textures with a feed-forward model to capture pose-dependent texture dynamics and illumination effects beyond simplified reflectance assumptions. Finally, a fine-tuned video-to-video diffusion model transforms the physically grounded renderings into temporally coherent, high-detail videos while preserving 3D control, with an error-recycling strategy for generating long videos. Experimental evaluations demonstrate our method's improved perceptual quality over prior relightable avatar baselines. Project Page: https://vcai.mpi-inf.mpg.de/projects/GRA/