A Neural-Network-Based Approach for Loose-Fitting Clothing

TL;DR

This paper presents a real-time neural network approach for simulating loose-fitting clothing by combining a numerical algorithm for ballistic features with neural skinning and a quasistatic neural network to efficiently model high-frequency deformations.

Contribution

It introduces a hybrid method that integrates a stable numerical approximation with neural skinning and QNNs for real-time, accurate clothing simulation.

Findings

Neural skinning outperforms linear blend skinning.

QNNs require less training data and generalize well.

The approach achieves real-time performance with high accuracy.

Abstract

Since loose-fitting clothing contains dynamic modes that have proven to be difficult to predict via neural networks, we first illustrate how to coarsely approximate these modes with a real-time numerical algorithm specifically designed to mimic the most important ballistic features of a classical numerical simulation. Although there is some flexibility in the choice of the numerical algorithm used as a proxy for full simulation, it is essential that the stability and accuracy be independent from any time step restriction or similar requirements in order to facilitate real-time performance. In order to reduce the number of degrees of freedom that require approximations to their dynamics, we simulate rigid frames and use skinning to reconstruct a rough approximation to a desirable mesh; as one might expect, neural-network-based skinning seems to perform better than linear blend skinning in this scenario. Improved high frequency deformations are subsequently added to the skinned mesh via a quasistatic neural network (QNN). In contrast to recurrent neural networks that require a plethora of training data in order to adequately generalize to new examples, QNNs perform well with significantly less training data.