Saved in:
Bibliographic Details
Main Authors: Liu, Aoran, Hu, Kun, Mo, Clinton Ansun, Wu, Qiuxia, Kang, Wenxiong, Wang, Zhiyong
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.15110
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909997033586688
author Liu, Aoran
Hu, Kun
Mo, Clinton Ansun
Wu, Qiuxia
Kang, Wenxiong
Wang, Zhiyong
author_facet Liu, Aoran
Hu, Kun
Mo, Clinton Ansun
Wu, Qiuxia
Kang, Wenxiong
Wang, Zhiyong
contents Garment simulation is fundamental to various applications in computer vision and graphics, from virtual try-on to digital human modelling. However, conventional physics-based methods remain computationally expensive, hindering their application in time-sensitive scenarios. While graph neural networks (GNNs) offer promising acceleration, existing approaches exhibit poor cross-resolution generalisation, demonstrating significant performance degradation on higher-resolution meshes beyond the training distribution. This stems from two key factors: (1) existing GNNs employ fixed message-passing depth that fails to adapt information aggregation to mesh density variation, and (2) vertex-wise displacement magnitudes are inherently resolution-dependent in garment simulation. To address these issues, we introduce Propagation-before-Update Graph Network (Pb4U-GNet), a resolution-adaptive framework that decouples message propagation from feature updates. Pb4U-GNet incorporates two key mechanisms: (1) dynamic propagation depth control, adjusting message-passing iterations based on mesh resolution, and (2) geometry-aware update scaling, which scales predictions according to local mesh characteristics. Extensive experiments show that even trained solely on low-resolution meshes, Pb4U-GNet exhibits strong generalisability across diverse mesh resolutions, addressing a fundamental challenge in neural garment simulation.
format Preprint
id arxiv_https___arxiv_org_abs_2601_15110
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Pb4U-GNet: Resolution-Adaptive Garment Simulation via Propagation-before-Update Graph Network
Liu, Aoran
Hu, Kun
Mo, Clinton Ansun
Wu, Qiuxia
Kang, Wenxiong
Wang, Zhiyong
Computer Vision and Pattern Recognition
Garment simulation is fundamental to various applications in computer vision and graphics, from virtual try-on to digital human modelling. However, conventional physics-based methods remain computationally expensive, hindering their application in time-sensitive scenarios. While graph neural networks (GNNs) offer promising acceleration, existing approaches exhibit poor cross-resolution generalisation, demonstrating significant performance degradation on higher-resolution meshes beyond the training distribution. This stems from two key factors: (1) existing GNNs employ fixed message-passing depth that fails to adapt information aggregation to mesh density variation, and (2) vertex-wise displacement magnitudes are inherently resolution-dependent in garment simulation. To address these issues, we introduce Propagation-before-Update Graph Network (Pb4U-GNet), a resolution-adaptive framework that decouples message propagation from feature updates. Pb4U-GNet incorporates two key mechanisms: (1) dynamic propagation depth control, adjusting message-passing iterations based on mesh resolution, and (2) geometry-aware update scaling, which scales predictions according to local mesh characteristics. Extensive experiments show that even trained solely on low-resolution meshes, Pb4U-GNet exhibits strong generalisability across diverse mesh resolutions, addressing a fundamental challenge in neural garment simulation.
title Pb4U-GNet: Resolution-Adaptive Garment Simulation via Propagation-before-Update Graph Network
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.15110