Saved in:
Bibliographic Details
Main Authors: Liu, Aoran, Hu, Kun, Mo, Clinton, Li, Changyang, Wang, Zhiyong
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.11763
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917986708750336
author Liu, Aoran
Hu, Kun
Mo, Clinton
Li, Changyang
Wang, Zhiyong
author_facet Liu, Aoran
Hu, Kun
Mo, Clinton
Li, Changyang
Wang, Zhiyong
contents 3D garment simulation is a critical component for producing cloth-based graphics. Recent advancements in graph neural networks (GNNs) offer a promising approach for efficient garment simulation. However, GNNs require extensive message-passing to propagate information such as physical forces and maintain contact awareness across the entire garment mesh, which becomes computationally inefficient at higher resolutions. To address this, we devise a novel GNN-based mesh learning framework with two key components to extend the message-passing range with minimal overhead, namely the Laplacian-Smoothed Dual Message-Passing (LSDMP) and the Geodesic Self-Attention (GSA) modules. LSDMP enhances message-passing with a Laplacian features smoothing process, which efficiently propagates the impact of each vertex to nearby vertices. Concurrently, GSA introduces geodesic distance embeddings to represent the spatial relationship between vertices and utilises attention mechanisms to capture global mesh information. The two modules operate in parallel to ensure both short- and long-range mesh modelling. Extensive experiments demonstrate the state-of-the-art performance of our method, requiring fewer layers and lower inference latency.
format Preprint
id arxiv_https___arxiv_org_abs_2504_11763
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Extended Short- and Long-Range Mesh Learning for Fast and Generalized Garment Simulation
Liu, Aoran
Hu, Kun
Mo, Clinton
Li, Changyang
Wang, Zhiyong
Computer Vision and Pattern Recognition
3D garment simulation is a critical component for producing cloth-based graphics. Recent advancements in graph neural networks (GNNs) offer a promising approach for efficient garment simulation. However, GNNs require extensive message-passing to propagate information such as physical forces and maintain contact awareness across the entire garment mesh, which becomes computationally inefficient at higher resolutions. To address this, we devise a novel GNN-based mesh learning framework with two key components to extend the message-passing range with minimal overhead, namely the Laplacian-Smoothed Dual Message-Passing (LSDMP) and the Geodesic Self-Attention (GSA) modules. LSDMP enhances message-passing with a Laplacian features smoothing process, which efficiently propagates the impact of each vertex to nearby vertices. Concurrently, GSA introduces geodesic distance embeddings to represent the spatial relationship between vertices and utilises attention mechanisms to capture global mesh information. The two modules operate in parallel to ensure both short- and long-range mesh modelling. Extensive experiments demonstrate the state-of-the-art performance of our method, requiring fewer layers and lower inference latency.
title Extended Short- and Long-Range Mesh Learning for Fast and Generalized Garment Simulation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.11763