Towards automatic digital garment assembly
Quick Answer
The paper presents two learning-based models for automating digital garment assembly from 2D patterns, achieving 63.3% seam recovery and 66.2% placement accuracy on a dataset of 4,035 garments.
Quick Take
These models integrate into CAD software, streamlining the garment design process significantly.
Key Points
- Automatic sewing model uses a Transformer encoder with multiple prediction heads.
- Achieves 63.3% accuracy in recovering seam and hem topologies.
- Panel-level model predicts body-region assignments and placement coordinates.
- 66.2% of test garments meet specified placement criteria.
- Models integrated into CAD software for streamlined garment assembly.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Creating digital garments from existing two-dimensional patterns remains a time-consuming process. Although patterns are widely available in digital form, their assembly in garment CAD software involves manual definition of sewing operations and arrangement of the pattern panels for drape simulation. We present two learning-based approaches that automate both tasks using the 2D vector pattern as their sole input. Our automatic sewing model operates at the segment level, leveraging a Transformer encoder with multiple prediction heads. Our novel architecture supports many-to-many, ordered segment correspondences, as well as hems, overlapping seams needed for multilayer garments, and construction properties such as seam allowances and stitch types, required for the finished virtual garment but neglected by previous methods. A complementary panel-level model predicts body-region assignments, layers, and placement coordinates to initialize the drape simulation. We evaluate both models on a curated dataset of 4,035 professionally assembled garment instances. The sewing model exactly recovers all seam and hem topologies of 63.3\% of test garments, while the arrangement model meets the specified placement criteria for all panels in 66.2\% of test garments. We also integrate both methods into garment CAD software, demonstrating automatic assembly of successfully predicted garments.
| Comments: | 11 pages, 8 figures |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Graphics (cs.GR) |
| Cite as: | arXiv:2610.20651 [cs.CV] |
| (or arXiv:2610.20651v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.20651 arXiv-issued DOI via DataCite |
Submission history
From: Alejandro Rodriguez [view email]
[v1]
Mon, 12 Oct 2026 16:16:09 UTC (11,999 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →ProMoE-FL: Prototype-conditioned Mixture of Experts for Multimodal Federated Learning with Missing Modalities
ProMoE-FL introduces a Prototype-conditioned Mixture-of-Experts framework for multimodal federated learning, effectively addressing missing modalities. It outperforms existing methods on four chest X-ray datasets, demonstrating superior feature synthesis capabilities in both homogeneous and heterogeneous settings.