Hierarchical Cloth Simulation using Deep Neural Networks

TL;DR

This paper introduces a hierarchical cloth simulation approach that combines traditional physics-based methods with deep neural networks to achieve fast, reliable, and detailed cloth animations for computer graphics.

Contribution

It presents a novel hierarchical framework integrating physics-based simulation with DNN inference for efficient cloth modeling.

Findings

The method produces reliable cloth simulations under various conditions.

It significantly speeds up the simulation process.

The approach maintains high detail and accuracy.

Abstract

Fast and reliable physically-based simulation techniques are essential for providing flexible visual effects for computer graphics content. In this paper, we propose a fast and reliable hierarchical cloth simulation method, which combines conventional physically-based simulation with deep neural networks (DNN). Simulations of the coarsest level of the hierarchical model are calculated using conventional physically-based simulations, and more detailed levels are generated by inference using DNN models. We demonstrate that our method generates reliable and fast cloth simulation results through experiments under various conditions.