NeuralClothSim: Neural Deformation Fields Meet the Thin Shell Theory

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kairanda, Navami, Habermann, Marc, Theobalt, Christian, Golyanik, Vladislav
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910687303827456
author Kairanda, Navami
Habermann, Marc
Theobalt, Christian
Golyanik, Vladislav
author_facet Kairanda, Navami
Habermann, Marc
Theobalt, Christian
Golyanik, Vladislav
contents 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 which surface deformation is encoded in neural network weights in the form of a neural field. Our memory-efficient solver operates on a new continuous coordinate-based surface representation called neural deformation fields (NDFs); it supervises NDF equilibria with the laws of the non-linear Kirchhoff-Love shell theory with a non-linear anisotropic material model. NDFs are adaptive: They 1) allocate their capacity to the deformation details and 2) allow surface state queries at arbitrary spatial resolutions without re-training. We show how to train NeuralClothSim while imposing hard boundary conditions and demonstrate multiple applications, such as material interpolation and simulation editing. The experimental results highlight the effectiveness of our continuous neural formulation. See our project page: https://4dqv.mpi-inf.mpg.de/NeuralClothSim/.
format Preprint
id arxiv_https___arxiv_org_abs_2308_12970
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle NeuralClothSim: Neural Deformation Fields Meet the Thin Shell Theory
Kairanda, Navami
Habermann, Marc
Theobalt, Christian
Golyanik, Vladislav
Graphics
Machine Learning
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 which surface deformation is encoded in neural network weights in the form of a neural field. Our memory-efficient solver operates on a new continuous coordinate-based surface representation called neural deformation fields (NDFs); it supervises NDF equilibria with the laws of the non-linear Kirchhoff-Love shell theory with a non-linear anisotropic material model. NDFs are adaptive: They 1) allocate their capacity to the deformation details and 2) allow surface state queries at arbitrary spatial resolutions without re-training. We show how to train NeuralClothSim while imposing hard boundary conditions and demonstrate multiple applications, such as material interpolation and simulation editing. The experimental results highlight the effectiveness of our continuous neural formulation. See our project page: https://4dqv.mpi-inf.mpg.de/NeuralClothSim/.
title NeuralClothSim: Neural Deformation Fields Meet the Thin Shell Theory
topic Graphics
Machine Learning
url https://arxiv.org/abs/2308.12970