HOOD: Hierarchical Graphs for Generalized Modelling of Clothing Dynamics

TL;DR

This paper introduces HOOD, a hierarchical graph neural network approach that predicts realistic clothing dynamics in real-time, handling various garment types, topologies, and material properties without garment-specific training.

Contribution

The paper presents a novel hierarchical message-passing scheme within graph neural networks that efficiently models complex clothing behaviors and topology changes at inference time.

Findings

Outperforms baseline methods quantitatively

Produces more realistic visual results

Handles topology and material variations at inference

Abstract

We propose a method that leverages graph neural networks, multi-level message passing, and unsupervised training to enable real-time prediction of realistic clothing dynamics. Whereas existing methods based on linear blend skinning must be trained for specific garments, our method is agnostic to body shape and applies to tight-fitting garments as well as loose, free-flowing clothing. Our method furthermore handles changes in topology (e.g., garments with buttons or zippers) and material properties at inference time. As one key contribution, we propose a hierarchical message-passing scheme that efficiently propagates stiff stretching modes while preserving local detail. We empirically show that our method outperforms strong baselines quantitatively and that its results are perceived as more realistic than state-of-the-art methods.