基于分层表示的解耦穿衣虚拟人生成
Disentangled Clothed Avatar Generation with Layered Representation
AI总结：
针对穿衣虚拟人组件难解耦的问题，提出基于分层UV特征平面表示的LayerAvatar方法，结合带约束的单阶段扩散模型，实现高解耦度的穿衣虚拟人生成，支持实时渲染与动画，可应用于组件迁移。
摘要：
穿衣虚拟人生成在虚拟现实、增强现实、电影制作等领域具有广泛应用。现有方法虽已在生成多样化数字虚拟人方面取得成功，但生成具备解耦组件（如身体、头发、衣物）的虚拟人长期以来是一项难题。本文提出LayerAvatar，这是首个基于前馈扩散的组件解耦穿衣虚拟人生成方法。为实现该目标，我们首先提出分层UV特征平面表示：各组件分布在基于高斯的UV特征平面的不同层中，并带有对应语义标签。该表示支持高分辨率实时渲染，也支持包含可控手势与面部表情的丰富动画效果。基于这一精心设计的表示，我们训练了单阶段扩散模型，并引入约束项以解决最内层人体层的严重遮挡问题。大量实验证明，我们的方法在生成解耦穿衣虚拟人方面表现出色，我们还进一步探索了其在组件迁移中的应用。项目页面地址为：https://olivia23333.github.io/LayerAvatar/
英文摘要：
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/
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
