Relightable Gaussian Codec Avatars

TL;DR

This paper introduces a high-fidelity, relightable head avatar model using 3D Gaussian geometry and a novel appearance model, enabling real-time rendering and animation with detailed features and diverse lighting conditions.

Contribution

The work presents a new Gaussian-based geometry and a learnable radiance transfer appearance model for realistic, relightable avatars capable of real-time performance and detailed expression animation.

Findings

Captures sub-millimeter details like hair strands and pores.

Achieves real-time relighting with all-frequency reflections.

Outperforms existing methods in fidelity and speed.

Abstract

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.