ContourCraft: Learning to Resolve Intersections in Neural Multi-Garment Simulations

TL;DR

This paper introduces extmoniker{}, a neural cloth simulation method that effectively resolves intersections and collisions in multi-layer garments using a novel intersection contour loss integrated with GNNs.

Contribution

The work presents a new intersection contour loss and a robust neural simulation framework that improves collision handling in multi-layer cloth simulations, even from intersected inputs.

Findings

Significantly reduces interpenetrations in neural cloth simulations.

Produces visually compelling and realistic multi-layer garment animations.

Effective across diverse dynamic human motions.

Abstract

Learning-based approaches to cloth simulation have started to show their potential in recent years. However, handling collisions and intersections in neural simulations remains a largely unsolved problem. In this work, we present \moniker{}, a learning-based solution for handling intersections in neural cloth simulations. Unlike conventional approaches that critically rely on intersection-free inputs, \moniker{} robustly recovers from intersections introduced through missed collisions, self-penetrating bodies, or errors in manually designed multi-layer outfits. The technical core of \moniker{} is a novel intersection contour loss that penalizes interpenetrations and encourages rapid resolution thereof. We integrate our intersection loss with a collision-avoiding repulsion objective into a neural cloth simulation method based on graph neural networks (GNNs). We demonstrate our method's ability across a challenging set of diverse multi-layer outfits under dynamic human motions. Our extensive analysis indicates that \moniker{} significantly improves collision handling for learned simulation and produces visually compelling results.