PEGASUS: Personalized Generative 3D Avatars with Composable Attributes
This addresses the need for customizable digital avatars in applications like virtual reality or gaming, though it appears incremental as it builds on existing generative modeling techniques.
The paper tackles the problem of creating personalized generative 3D face avatars from monocular video, enabling disentangled control over facial attributes like hair or nose while preserving identity, and demonstrates effectiveness through experiments showing high realism and identity preservation.
We present PEGASUS, a method for constructing a personalized generative 3D face avatar from monocular video sources. Our generative 3D avatar enables disentangled controls to selectively alter the facial attributes (e.g., hair or nose) while preserving the identity. Our approach consists of two stages: synthetic database generation and constructing a personalized generative avatar. We generate a synthetic video collection of the target identity with varying facial attributes, where the videos are synthesized by borrowing the attributes from monocular videos of diverse identities. Then, we build a person-specific generative 3D avatar that can modify its attributes continuously while preserving its identity. Through extensive experiments, we demonstrate that our method of generating a synthetic database and creating a 3D generative avatar is the most effective in preserving identity while achieving high realism. Subsequently, we introduce a zero-shot approach to achieve the same goal of generative modeling more efficiently by leveraging a previously constructed personalized generative model.