Presentation

<
PatternGSL: A Structured Specification Language for Template-Free and Simulation-Ready 3D Garments
SessionGarments
DescriptionWe present PatternGSL, a structured and template-free representation for simulation-ready 3D garments. Given a single garment image, our VLM-based method predicts editable sewing patterns with explicit panel, edge, and stitch topology. Trained on the large-scale PatternGSLData dataset, it enables accurate reconstruction, cloth simulation, and downstream garment design workflows.
Authors
Zhenyang Li
The University of Hong Kong (HKU)
Tsinghua University, China
Lutao Jiang
The Hong Kong University of Science and Technology (Guangzhou)
Yizhou Zhao
Carnegie Mellon University
Weikai Chen
LIGHTSPEED
Ying-Cong Chen
The Hong Kong University of Science and Technology (Guangzhou)
The Hong Kong University of Science and Technology
Xin Wang
LIGHTSPEED
Yifan Peng
The University of Hong Kong (HKU)
Event Type
Technical Paper
TimeThursday, 23 July 20262:10pm - 2:20pm PDT
LocationRoom 403 B
Digital Library PDF
Session Time & Location
Sunday, 19 July 20266:00pm - 8:45pm PDTHall K
Thursday, 23 July 20262:00pm - 3:30pm PDTRoom 403 B
Keywords
Artificial Intelligence/Machine Learning
Geometry
Registration Categories
Full Conference Supporter
Full Conference
Next PresentationNext PresentationGarment Particles: A 2D–3D Symmetric Garment Representation for Generation and Editing
Similar Presentations
Garment Particles: A 2D–3D Symmetric Garment Representation for Generation and Editing
LoBoFit: Flexible Garment Refitting via Local Bone Mapping Blending
CasLayout: Cascaded 3D Layout Diffusion for Indoor Scene Synthesis with Implicit Relation Modeling