Affiliation:
1. Zhejiang University China
2. ZJU‐Tencent Game and Intelligent Graphics Innovation Technology Joint Lab China
3. Tencent China
Abstract
AbstractWe propose a three‐stage network that utilizes a skinning‐based model to accurately predict dynamic cloth deformation. Our approach decomposes cloth deformation into three distinct components: static, coarse dynamic, and wrinkle dynamic components. To capture these components, we train our three‐stage network accordingly. In the first stage, the static component is predicted by constructing a static skinning model that incorporates learned joint increments and skinning weight increments. Then, in the second stage, the coarse dynamic component is added to the static skinning model by incorporating serialized skeleton information. Finally, in the third stage, the mesh sequence stage refines the prediction by incorporating the wrinkle dynamic component using serialized mesh information. We have implemented our network and used it in a Unity game scene, enabling real‐time prediction of cloth dynamics. Our implementation achieves impressive prediction speeds of approximately 3.65ms using an NVIDIA GeForce RTX 3090 GPU and 9.66ms on an Intel i7‐7700 CPU. Compared to SOTA methods, our network excels in accurately capturing fine dynamic cloth deformations.
Funder
National Natural Science Foundation of China
Subject
Computer Graphics and Computer-Aided Design
Reference39 articles.
1. Robust treatment of collisions, contact and friction for cloth animation
2. Ba Jimmy Lei Kiros Jamie Ryan andHinton Geoffrey E.“Layer normalization”.arXiv preprint arXiv:1607.06450(2016) 6.
3. PBNS
4. Neural Cloth Simulation
5. Projective Dynamics: Fusing Constraint Projections for Fast Simulation;Bouaziz Sofien;ACM Trans. Graph. (SIGGRAPH),2014