GarmageNet: A Multimodal Generative Framework for Sewing Pattern Design and Generic Garment Modeling
ACM Transactions on Graphics · 2025-12 · 44 (6) · 1-23
DOI: 10.1145/3763271 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 04.12.2025. Verfasst von Siran Li und 7 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 94 Literaturangaben. Gefördert von: Key R&D Program of Zhejiang.
Abstract (Originalsprache)
Realistic digital garment modeling remains a labor-intensive task due to the intricate process of translating 2D sewing patterns into high-fidelity, simulation-ready 3D garments. We introduce GarmageNet , a unified generative framework that automates the creation of 2D sewing patterns, the construction of sewing relationships, and the synthesis of 3D garment initializations compatible with physics-based simulation. Central to our approach is Garmage , a novel garment representation that encodes each panel as a structured geometry image, effectively bridging the semantic and geometric gap between 2D structural patterns and 3D garment geometries. Followed by GarmageNet , a latent diffusion transformer to synthesize panel-wise geometry images and GarmageJigsaw , a neural module for predicting point-to-point sewing connections along panel contours. To support training and evaluation, we build GarmageSet , a large-scale dataset comprising 14,801 professionally designed garments with detailed structural and style annotations. Our method demonstrates versatility and efficacy across multiple application scenarios, including scalable garment generation from multi-modal design concepts (text prompts, sketches, photographs), automatic modeling from raw flat sewing patterns, pattern recovery from unstructured point clouds, and progressive garment editing using conventional instructions, laying the foundation for fully automated, production-ready pipelines in digital fashion. Refer to our project page for open-sourced code and dataset.
Förderung
- Key R&D Program of Zhejiang
Zitieren
APA
Li, S., Liu, R., Liu, C., Wang, Z., He, G., Li, Y., Jin, X., & Wang, H. (2025). GarmageNet: A Multimodal Generative Framework for Sewing Pattern Design and Generic Garment Modeling. ACM Transactions on Graphics, 44(6), 1-23. https://doi.org/10.1145/3763271
Vancouver
Li S, Liu R, Liu C, Wang Z, He G, Li Y, et al. GarmageNet: A Multimodal Generative Framework for Sewing Pattern Design and Generic Garment Modeling. ACM Transactions on Graphics. 2025;44(6):1-23. doi:10.1145/3763271
BibTeX
@article{Li2025,
author = {Li, Siran and Liu, Ruiyang and Liu, Chen and Wang, Zhendong and He, Gaofeng and Li, Yong-Lu and Jin, Xiaogang and Wang, Huamin},
title = {GarmageNet: A Multimodal Generative Framework for Sewing Pattern Design and Generic Garment Modeling},
journal = {ACM Transactions on Graphics},
year = {2025},
volume = {44},
number = {6},
pages = {1--23},
doi = {10.1145/3763271}
}
EUVIMED