Disentangled Clothed Avatar Generation with Layered Representation

TL;DR

LayerAvatar is a novel diffusion-based method that generates high-resolution, disentangled clothed avatars with controllable features using a layered UV representation, enabling real-time rendering and animation.

Contribution

It introduces a layered UV feature plane representation and a single-stage diffusion model for component-disentangled avatar generation, addressing occlusion issues.

Findings

High-quality, disentangled avatar generation demonstrated

Supports real-time rendering and expressive animation

Effective component transfer capabilities

Abstract

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/