Frequency-Guided Self-Supervised Wind-Driven Garment Animation Simulation

Simple item page
dc.contributor.authorShi, Minen_US
dc.contributor.authorLi, Zhenyuen_US
dc.contributor.authorMao, Tianluen_US
dc.contributor.authorZhu, Dengmingen_US
dc.contributor.authorWang, Suqingen_US
dc.contributor.editorChristie, Marcen_US
dc.contributor.editorHan, Ping-Hsuanen_US
dc.contributor.editorLin, Shih-Syunen_US
dc.contributor.editorPietroni, Nicoen_US
dc.contributor.editorSchneider, Teseoen_US
dc.contributor.editorTsai, Hsin-Rueyen_US
dc.contributor.editorWang, Yu-Shuenen_US
dc.contributor.editorZhang, Eugeneen_US
dc.date.accessioned2025-10-07T06:05:20Z
dc.date.available2025-10-07T06:05:20Z
dc.date.issued2025
dc.description.abstractRealistic simulation of garment deformation under coupled multi-physical fields remains a critical challenge in 3D animation, primarily due to diverse properties of fabric and complex interactions with external forces. Existing methods predominantly focus on human-driven garment animation and struggle with complex environmental factors such as wind fields, while supervised learning methods suffer from strong data dependency and limited generalization. We propose FWGNet, a self-supervised training framework based on GNNs that models the garment-human-wind interaction as an integrated physical system. The framework is trained using differentiable physics-based constraints. A key component is a wind feature encoder that employs wavelet transforms to map wind velocity sequences into the frequency domain, effectively capturing multi-scale turbulence effects on fabric behavior. To eliminate dependence on large datasets, we introduce physics-informed loss functions that incorporate gravitational potential energy, aerodynamic wind forces, and fabric deformation constraints. Experiments demonstrate that our approach produces highly realistic visual effects, such as detailed wrinkle formation and fabric fluttering under dynamic wind conditions. Quantitative evaluations across multiple metrics confirm that FWGNet achieves a strong balance between physical accuracy and visual realism, particularly in complex scenarios involving coupled physical interactions.en_US
dc.description.sectionheadersPosters and Demos
dc.description.seriesinformationPacific Graphics Conference Papers, Posters, and Demos
dc.identifier.doi10.2312/pg.20251308
dc.identifier.isbn978-3-03868-295-0
dc.identifier.pages2 pages
dc.identifier.urihttps://doi.org/10.2312/pg.20251308
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/pg20251308
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies → Animation
dc.subjectComputing methodologies → Animation
dc.titleFrequency-Guided Self-Supervised Wind-Driven Garment Animation Simulationen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
pg20251308.pdf
Size:
3.44 MB
Format:
Adobe Portable Document Format
Download
Collections
PG2025 Conference Papers, Posters, and Demos