Disentangled Clothed Avatar Generation with Layered Representation
This addresses a problem in virtual and augmented reality and filmmaking by enabling component-disentangled avatar generation, though it appears incremental as it builds on existing diffusion methods.
The paper tackles the challenge of generating clothed avatars with disentangled components like body, hair, and clothes, proposing LayerAvatar, a feed-forward diffusion-based method that achieves high-resolution, real-time rendering and expressive animation.
Clothed avatar generation has wide applications in virtual and augmented reality, filmmaking, and more. Previous methods have achieved success in generating diverse digital avatars, however, generating avatars with disentangled components (\eg, body, hair, and clothes) has long been a challenge. In this paper, we propose LayerAvatar, the first feed-forward diffusion-based method for generating component-disentangled clothed avatars. To achieve this, we first propose a layered UV feature plane representation, where components are distributed in different layers of the Gaussian-based UV feature plane with corresponding semantic labels. This representation supports high-resolution and real-time rendering, as well as expressive animation including controllable gestures and facial expressions. Based on the well-designed representation, we train a single-stage diffusion model and introduce constrain terms to address the severe occlusion problem of the innermost human body layer. Extensive experiments demonstrate the impressive performances of our method in generating disentangled clothed avatars, and we further explore its applications in component transfer. The project page is available at: https://olivia23333.github.io/LayerAvatar/