NeuralClothSim: Neural Deformation Fields Meet the Thin Shell Theory

arXiv:2308.12970v2 Announce Type: replace-cross
Abstract: Despite existing 3D cloth simulators producing realistic results, they predominantly operate on discrete surface representations (e.g. points and meshes) with a fixed spatial resolution, which often leads to large memory consumption and resolution-dependent simulations. Moreover, back-propagating gradients through the existing solvers is difficult, and they cannot be easily integrated into modern neural architectures. In response, this paper re-thinks physically plausible cloth simulation: We propose NeuralClothSim, i.e., a new quasistatic cloth simulator using thin shells, in …

abstract arxiv consumption cs.gr cs.lg fields leads memory memory consumption meshes replace resolution results shell simulations spatial surface theory through type