We propose a method that leverages graph neural networks, multi-level message passing, and unsupervised training to enable real-time prediction of realistic clothing dynamics. Whereas existing methods based on linear blend skinning must be trained for specific garments, our method is agnostic to body shape and applies to tight-fitting garments as well as loose, free-flowing clothing. Our method furthermore handles changes in topology (e.g., garments with buttons or zippers) and material properties at inference time. As one key contribution, we propose a hierarchical message-passing scheme that efficiently propagates stiff stretching modes while preserving local detail. We empirically show that our method outperforms strong baselines quantitatively and that its results are perceived as more realistic than state-of-the-art methods.

翻译：我们提出了一种方法，该方法利用图神经网络、多层次消息传递和无监督训练，实现对真实服装动力学的实时预测。现有的基于线性混合蒙皮的方法必须针对特定服装进行训练，而我们的方法则不依赖于体形，既适用于紧身服装，也适用于宽松飘逸的衣物。此外，我们的方法还能在推理时处理拓扑变化（例如，带有纽扣或拉链的服装）和材料属性。作为一项关键贡献，我们提出了一种分层消息传递方案，该方案在保持局部细节的同时，有效传播了刚性的拉伸模式。实验表明，我们的方法在定量上优于强基线方法，且其结果比现有最先进方法更真实。