GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learning

arXiv:2312.11461v2 Announce Type: replace-cross
Abstract: Gaussian splatting has emerged as a powerful 3D representation that harnesses the advantages of both explicit (mesh) and implicit (NeRF) 3D representations. In this paper, we seek to leverage Gaussian splatting to generate realistic animatable avatars from textual descriptions, addressing the limitations (e.g., flexibility and efficiency) imposed by mesh or NeRF-based representations. However, a naive application of Gaussian splatting cannot generate high-quality animatable avatars and suffers from learning instability; it also cannot capture fine avatar …

abstract advantages arxiv avatars cs.cv cs.gr cs.lg efficiency flexibility generate limitations mesh nerf paper representation textual type