This paper addresses the task of 3D clothed human generation from textural descriptions. Previous works usually encode the human body and clothes as a holistic model and generate the whole model in a single-stage optimization, which makes them struggle for clothing editing and meanwhile lose fine-grained control over the whole generation process. To solve this, we propose a layer-wise clothed human representation combined with a progressive optimization strategy, which produces clothing-disentangled 3D human models while providing control capacity for the generation process. The basic idea is progressively generating a minimal-clothed human body and layer-wise clothes. During clothing generation, a novel stratified compositional rendering method is proposed to fuse multi-layer human models, and a new loss function is utilized to help decouple the clothing model from the human body. The proposed method achieves high-quality disentanglement, which thereby provides an effective way for 3D garment generation. Extensive experiments demonstrate that our approach achieves state-of-the-art 3D clothed human generation while also supporting cloth editing applications such as virtual try-on. Project page: http://jtdong.com/tela_layer/

翻译：本文探讨从文本描述生成三维穿衣人体的任务。以往工作通常将人体与衣物编码为整体模型，并通过单阶段优化生成完整模型，导致难以进行衣物编辑且缺乏对生成过程的细粒度控制。为解决此问题，我们提出一种分层穿衣人体表示结合渐进式优化策略，可在生成过程中提供控制能力的同时，产生衣物解耦的三维人体模型。核心思想是渐进生成最小衣物人体与分层衣物。在衣物生成阶段，提出一种新颖的分层组合渲染方法来融合多层人体模型，并利用新型损失函数辅助衣物模型与人体模型的解耦。所提方法实现了高质量解耦，从而为三维服装生成提供了有效途径。大量实验表明，我们的方法在三维穿衣人体生成中达到最先进水平，同时支持虚拟试穿等衣物编辑应用。项目页面：http://jtdong.com/tela_layer/