DiffusionAvatars: Deferred Diffusion for High-fidelity 3D Head Avatars

arXiv:2311.18635v2 Announce Type: replace
Abstract: DiffusionAvatars synthesizes a high-fidelity 3D head avatar of a person, offering intuitive control over both pose and expression. We propose a diffusion-based neural renderer that leverages generic 2D priors to produce compelling images of faces. For coarse guidance of the expression and head pose, we render a neural parametric head model (NPHM) from the target viewpoint, which acts as a proxy geometry of the person. Additionally, to enhance the modeling of intricate facial expressions, we …

abstract arxiv avatar avatars control cs.cv diffusion fidelity guidance head images person type