One2Avatar: Generative Implicit Head Avatar For Few-shot User Adaptation

arXiv:2402.11909v1 Announce Type: new
Abstract: Traditional methods for constructing high-quality, personalized head avatars from monocular videos demand extensive face captures and training time, posing a significant challenge for scalability. This paper introduces a novel approach to create high quality head avatar utilizing only a single or a few images per user. We learn a generative model for 3D animatable photo-realistic head avatar from a multi-view dataset of expressions from 2407 subjects, and leverage it as a prior for creating personalized …

abstract arxiv avatar avatars challenge cs.cv demand face few-shot generative head images novel paper per personalized quality scalability training type videos