Reproduce “Analytically Integratable Zero-restlength Springs for Capturing Dynamic Modes unrepresented by Quasistatic Neural Networks” 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, Yushan Han, Zhenglin Geng, Joseph Teran, Ronald Fedkiw
The authors combine pose-conditioned deformation and analytic springs for soft-tissue animation on human bodies. A quasistatic neural network corrects each pose, while damped springs follow moving targets and capture motion dependent on history. The network uses about 5,000 poses; springs use a few dynamic examples. They report 30–90 frames per second and show qualitative results on one held-out motion.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.