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

2026-01-21

AI Summary

This work addresses the limited generalization of existing graph neural network approaches in cloth simulation to high-resolution meshes. The authors propose a resolution-adaptive simulation framework that decouples message propagation from feature updating and introduces two key mechanisms: dynamic control of propagation depth and geometry-aware update scaling. This design enables efficient modeling across varying mesh densities. Notably, the model is trained exclusively on low-resolution meshes yet maintains high accuracy when applied to unseen high-resolution configurations, significantly enhancing cross-resolution generalization. The approach effectively overcomes a critical bottleneck in neural cloth simulation by eliminating the need for retraining or fine-tuning at higher resolutions.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Web Mining and Content Analysis: Web data generation and simulation

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.

Problem

• garment simulation
• cross-resolution generalisation
• graph neural networks
• mesh resolution
• neural simulation

Innovation

• resolution-adaptive
• graph neural network
• garment simulation
• dynamic propagation
• geometry-aware scaling