Relightable Gaussian Codec Avatars
This work addresses the challenge of realistic avatar rendering for applications like VR, though it appears incremental by building on existing Gaussian and relighting techniques.
The paper tackles the problem of creating high-fidelity, relightable head avatars with real-time performance by developing a geometry model using 3D Gaussians to capture sub-millimeter details like hair strands and pores, and a novel appearance model based on learnable radiance transfer with spherical harmonics and Gaussians for efficient relighting under various illumination conditions, achieving superior results compared to existing approaches while maintaining real-time performance.
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.