发表机构
Inria Centre at the University Grenoble Alpes; InterDigital Inc.; Inria, University of Rennes, CNRS, IRISA-UMR 6074（格勒诺布尔阿尔卑斯大学Inria中心; InterDigital公司; Inria、雷恩大学、法国国家科学研究中心、IRISA-UMR 6074）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出DiT-Garment，利用2D扩散变换器在UV空间学习3D服装变形，支持任意姿态、未见设计和物理材质，训练于合成数据，泛化至真实服装。
AI 中文摘要
我们提出DiT-Garment，用于在任意运动的人体模型上建模动态3D服装。与现有方法不同，DiT-Garment能够为未见过的设计和物理材质的服装制作动画，同时允许对任何目标姿态的变形进行直接推断。为实现这一目标，我们利用2D扩散变换器架构在2D UV空间中学习3D变形。由于结果是非确定性的，我们的生成模型学习可能结果的分布。模板服装表示为与标准化姿态下的3D人体模型空间对齐的3D三角网格。为了处理不同的服装设计而无需共同模板或复杂的图卷积操作，扩散变换器以模板的3D位置图（在UV空间中表示）为条件，从而能够隐式学习标准姿态下身体周围3D空间的变形。进一步以身体运动和物理参数为条件，使模型具有物理基础。我们在合成数据和真实数据上对DiT-Garment进行了定量和定性评估。尽管仅在自动生成的布料设计的合成模拟上训练，我们的方法能够泛化到捕捉的和艺术家制作的服装设计。代码和数据可在该https URL上用于研究目的。
英文摘要
We present DiT-Garment to model dynamic 3D clothing over human body models in arbitrary motion. Unlike existing methods, DiT-Garment can animate garments with unseen designs and physical materials, while allowing for direct inference of deformations for any target pose. To achieve this, we leverage a 2D diffusion transformer architecture to learn 3D deformations in a 2D UV-space. As the result is non-deterministic, our generative model learns the distribution of possible outcomes. The template garment is represented as a 3D triangle mesh spatially aligned with a 3D human body model in a standardized pose. To work with different garment designs without the need of a common template or complex graph convolution operations, the diffusion transformer is conditioned on a 3D position map of the template, represented in UV-space, which allows to implicitly learn a deformation of the 3D space around the body in standard pose. Further conditioning on body motion and physical parameters allows to physically ground the model. We quantitatively and qualitatively evaluate DiT-Garment on both synthetic and real data. While only trained on synthetic simulations of automatically generated cloth designs, our method generalizes to captured and artist-made garment designs. Code and data are available for research purposes at https://dumoulina.github.io/dit-garment/.
