GarmageNet: A Multimodal Generative Framework for Sewing Pattern Design and Generic Garment Modeling

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Siran, Liu, Ruiyang, Liu, Chen, Wang, Zhendong, He, Gaofeng, Li, Yong-Lu, Jin, Xiaogang, Wang, Huamin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908590346862592
author Li, Siran
Liu, Ruiyang
Liu, Chen
Wang, Zhendong
He, Gaofeng
Li, Yong-Lu
Jin, Xiaogang
Wang, Huamin
author_facet Li, Siran
Liu, Ruiyang
Liu, Chen
Wang, Zhendong
He, Gaofeng
Li, Yong-Lu
Jin, Xiaogang
Wang, Huamin
contents 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. Project page: https://style3d.github.io/garmagenet/.
format Preprint
id arxiv_https___arxiv_org_abs_2504_01483
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GarmageNet: A Multimodal Generative Framework for Sewing Pattern Design and Generic Garment Modeling
Li, Siran
Liu, Ruiyang
Liu, Chen
Wang, Zhendong
He, Gaofeng
Li, Yong-Lu
Jin, Xiaogang
Wang, Huamin
Graphics
Computer Vision and Pattern Recognition
I.3.5; I.2.10
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. Project page: https://style3d.github.io/garmagenet/.
title GarmageNet: A Multimodal Generative Framework for Sewing Pattern Design and Generic Garment Modeling
topic Graphics
Computer Vision and Pattern Recognition
I.3.5; I.2.10
url https://arxiv.org/abs/2504.01483