Garment representation, animation and editing is a challenging topic in the area of computer vision and graphics. Existing methods cannot perform smooth and reasonable garment transition under different shape styles and topologies. In this work, we introduce a novel method, termed as DeepCloth, to establish a unified garment representation framework enabling free and smooth garment style transition. Our key idea is to represent garment geometry by a "UV-position map with mask", which potentially allows the description of various garments with different shapes and topologies. Furthermore, we learn a continuous feature space mapped from the above UV space, enabling garment shape editing and transition by controlling the garment features. Finally, we demonstrate applications of garment animation, reconstruction and editing based on our neural garment representation and encoding method. To conclude, with the proposed DeepCloth, we move a step forward on establishing a more flexible and general 3D garment digitization framework. Experiments demonstrate that our method can achieve the state-of-the-art garment modeling results compared with the previous methods.

本文提出了 DeepCloth，它是一个针对服装表示、重建、动画和编辑的统一框架，它包含了三个组件：拓扑感知的 UV 位置图、连续特征空间中的嵌入和服装动画方法。这个方法可以实现更加灵活、通用的3D服装数字化框架。

DeepCloth: 基于神经网络的服装表征方法用于形状和风格编辑