Reproduce “A Neural-Network-Based Approach for Loose-Fitting Clothing” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Yongxu Jin, Dalton Omens, Zhenglin Geng, Joseph Teran, Abishek Kumar, Kenji Tashiro, Ronald Fedkiw
The authors present a hybrid cloth-animation method that uses rope-chain physics to carry loose garments’ ballistic motion and neural networks to reconstruct coarse and fine cloth shape. For a cape with 12,690 vertices, 10 rope chains reduce degrees of freedom by about 90-fold. The result has dynamics similar to Houdini cloth, but collision handling is not guaranteed for out-of-distribution inputs.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.