GTAvatar: Bridging Gaussian Splatting and Texture Mapping for Relightable and Editable Gaussian Avatars
This addresses the need for editable avatars in visual effects, videoconferencing, and virtual reality, offering an incremental improvement by combining existing techniques.
The paper tackles the problem of creating relightable and editable head avatars by bridging Gaussian Splatting and texture mapping, achieving accurate reconstructions from a single monocular video with intuitive controls for appearance and geometry modifications.
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.