用分层表示生成可拆解的穿衣虚拟人，支持高分辨率实时渲染。
Disentangled Clothed Avatar Generation with Layered Representation
- 提出分层UV特征平面，将身体、头发、衣服分置不同层。
- 单阶段扩散模型生成高清虚拟人，支持可控表情与动作。
- 适合虚拟试衣、影视角色设计等需要部件分离的应用。
穿衣虚拟人生成在虚拟现实、增强现实及影视制作中应用广泛。现有方法虽能生成多样数字形象，但实现身体、头发、衣物等组件的解耦生成仍具挑战。本文提出LayerAvatar，首个基于前馈扩散模型的组件解耦穿衣虚拟人生成方法。通过设计分层高斯UV特征平面，将各组件分布于不同层并附语义标签，支持高分辨率实时渲染及可控表情与动作表达。基于此结构，训练单阶段扩散模型，并引入约束项解决最内层人体严重遮挡问题。大量实验验证了该方法在生成解耦穿衣虚拟人方面的优异性能，进一步探索了部件迁移应用。项目主页：https://olivia23333.github.io/LayerAvatar/
原文摘要 · Abstract (English)
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/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。