N-Cloth: Predicting 3D Cloth Deformation with Mesh-Based Networks

TL;DR

N-Cloth is a mesh-based neural network that predicts realistic 3D cloth deformations from initial cloth states and obstacle meshes, capable of handling complex scenes with high efficiency and outperforming prior methods.

Contribution

The paper introduces a general mesh-based learning approach using graph convolution for fast, plausible 3D cloth deformation prediction across arbitrary topologies.

Findings

Handles cloth meshes with up to 100K triangles.

Predicts deformations at 30-45 fps on high-end GPU.

Outperforms prior learning-based and physically-based methods.

Abstract

We present a novel mesh-based learning approach (N-Cloth) for plausible 3D cloth deformation prediction. Our approach is general and can handle cloth or obstacles represented by triangle meshes with arbitrary topologies. We use graph convolution to transform the cloth and object meshes into a latent space to reduce the non-linearity in the mesh space. Our network can predict the target 3D cloth mesh deformation based on the initial state of the cloth mesh template and the target obstacle mesh. Our approach can handle complex cloth meshes with up to 100K triangles and scenes with various objects corresponding to SMPL humans, non-SMPL humans or rigid bodies. In practice, our approach can be used to generate plausible cloth simulation at 30-45 fps on an NVIDIA GeForce RTX 3090 GPU. We highlight its benefits over prior learning-based methods and physically-based cloth simulators.