One2Avatar: Generative Implicit Head Avatar For Few-shot User Adaptation
This addresses the scalability challenge in personalized avatar creation for users, though it is incremental as it builds on prior 3D-aware generative models.
The paper tackles the problem of creating high-quality, personalized 3D head avatars from only a single or few images, reducing the need for extensive captures and training. It demonstrates compelling results and outperforms state-of-the-art methods for few-shot avatar adaptation.
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 avatar from few-shot images. Different from previous 3D-aware face generative models, our prior is built with a 3DMM-anchored neural radiance field backbone, which we show to be more effective for avatar creation through auto-decoding based on few-shot inputs. We also handle unstable 3DMM fitting by jointly optimizing the 3DMM fitting and camera calibration that leads to better few-shot adaptation. Our method demonstrates compelling results and outperforms existing state-of-the-art methods for few-shot avatar adaptation, paving the way for more efficient and personalized avatar creation.