Pb4U-GNet: Resolution-Adaptive Garment Simulation via Propagation-before-Update Graph Network

TL;DR

Pb4U-GNet is a novel graph neural network framework for garment simulation that adaptively adjusts message passing and scaling to handle varying mesh resolutions, enabling better generalization across different levels of detail.

Contribution

The paper introduces Pb4U-GNet, a resolution-adaptive GNN that decouples message propagation from feature updates, improving cross-resolution generalization in garment simulation.

Findings

Pb4U-GNet outperforms existing methods on high-resolution meshes.

The model generalizes well even when trained only on low-resolution data.

It achieves real-time performance in garment simulation tasks.

Abstract

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.