NeuralClothSim: Neural Deformation Fields Meet the Thin Shell Theory

TL;DR

NeuralClothSim introduces a neural network-based cloth simulation method using continuous deformation fields that are memory-efficient, resolution-adaptive, and compatible with modern neural architectures, based on thin shell theory.

Contribution

It proposes NeuralClothSim, a novel neural cloth simulator using neural deformation fields and thin shell theory, enabling resolution-independent, memory-efficient, and physically plausible cloth simulation.

Findings

Memory-efficient neural cloth simulation with NDFs.

Resolution-adaptive surface deformation queries.

Effective training with boundary conditions and applications.

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 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/.