GTAvatar: Bridging Gaussian Splatting and Texture Mapping for Relightable and Editable Gaussian Avatars

TL;DR

This paper introduces GTAvatar, a method that combines Gaussian Splatting with UV texture mapping to create relightable, editable 3D head avatars from monocular videos, enhancing realism and user control.

Contribution

It presents a novel approach that embeds Gaussian primitives into UV space for continuous, editable textures, enabling relighting and editing without extra optimization.

Findings

High-fidelity avatar reconstruction from monocular video

Effective relighting and editing of avatars

Outperforms state-of-the-art in accuracy and control

Abstract

Recent advancements in Gaussian Splatting have enabled increasingly accurate reconstruction of photorealistic head avatars, opening the door to numerous applications in visual effects, videoconferencing, and virtual reality. This, however, comes with the lack of intuitive editability offered by traditional triangle mesh-based methods. In contrast, we propose a method that combines the accuracy and fidelity of 2D Gaussian Splatting with the intuitiveness of UV texture mapping. By embedding each canonical Gaussian primitive's local frame into a patch in the UV space of a template mesh in a computationally efficient manner, we reconstruct continuous editable material head textures from a single monocular video on a conventional UV domain. Furthermore, we leverage an efficient physically based reflectance model to enable relighting and editing of these intrinsic material maps. Through extensive comparisons with state-of-the-art methods, we demonstrate the accuracy of our reconstructions, the quality of our relighting results, and the ability to provide intuitive controls for modifying an avatar's appearance and geometry via texture mapping without additional optimization.