ContourCraft: Learning to Resolve Intersections in Neural Multi-Garment Simulations
paper arXiv project video code
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 ContourCraft, a learning-based solution for handling intersections in neural cloth simulations. Unlike conventional approaches that critically rely on intersection-free inputs, ContourCraft robustly recovers from intersections introduced through missed collisions, self-penetrating bodies, or errors in manually designed multi-layer outfits. The technical core of ContourCraft 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 ContourCraft significantly improves collision handling for learned simulation and produces visually compelling results.
| Author(s): | Grigorev, Artur and Becherini, Giorgio and Black, Michael and Hilliges, Otmar and Thomaszewski, Bernhard |
| Links: | |
| Book Title: | ACM SIGGRAPH 2024 Conference Papers |
| Pages: | 1--10 |
| Year: | 2024 |
| Month: | July |
| Series: | SIGGRAPH '24 |
| Publisher: | Association for Computing Machinery |
| Project(s): | |
| BibTeX Type: | Conference Paper (inproceedings) |
| Address: | New York, NY, USA |
| DOI: | 10.1145/3641519.3657408 |
| State: | Published |
| URL: | https://dolorousrtur.github.io/contourcraft/ |
| Article Number: | 81 |
BibTeX
@inproceedings{ContourCraft:2024,
title = {{ContourCraft}: Learning to Resolve Intersections in Neural Multi-Garment Simulations},
booktitle = {ACM SIGGRAPH 2024 Conference Papers},
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 ContourCraft, a learning-based solution for handling intersections in neural cloth simulations. Unlike conventional approaches that critically rely on intersection-free inputs, ContourCraft robustly recovers from intersections introduced through missed collisions, self-penetrating bodies, or errors in manually designed multi-layer outfits. The technical core of ContourCraft 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 ContourCraft significantly improves collision handling for learned simulation and produces visually compelling results.},
pages = {1--10},
series = {SIGGRAPH '24},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
month = jul,
year = {2024},
author = {Grigorev, Artur and Becherini, Giorgio and Black, Michael and Hilliges, Otmar and Thomaszewski, Bernhard},
doi = {10.1145/3641519.3657408},
url = {https://dolorousrtur.github.io/contourcraft/},
month_numeric = {7}
}