Automatic Sewing Pattern Generation from Garment Images Using Segmentation and Conditional GANs

An automatic method for generating sewing patterns corresponding to dress images is proposed in this study. In garment production, the creation of sewing patterns, the blueprints for garment construction, from design sketches is a highly complex process that demands substantial expertise and experience. Most existing studies focus on learning from entire garments; however, they face the challenge of reduced shape reproduction accuracy for small parts with diverse shapes, such as collars and sleeves. The proposed method segments a garment image into three main parts—bodice, sleeve, and collar—and inputs each part into a specialized sewing pattern generation model, enabling faithful reproduction of even small and complex garment parts. A custom training dataset consisting of garment images and their corresponding sewing pattern images used in actual garment production is constructed. In addition, a part segmentation model and part-specific GAN-based sewing pattern generation models are developed. The proposed method is capable of adapting to diverse garment shapes and variations across parts, thereby enhancing both the accuracy and efficiency of sewing pattern creation in garment production workflows.

• Publication year

  2026

• Venue

  IEEE/SICE International Symposium on System Integration

• Publication date

  2026-01-11

• Fields of study

  Not labeled

• Identifiers
  DOI 10.1109/SII64115.2026.11404641
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Realistic Sewing Pattern Generation and Dataset Construction for Gan-Based Fashion Synthesis

  2025cited by this paper
• SAM 2: Segment Anything in Images and Videos

  2024influential reference
• Towards Garment Sewing Pattern Reconstruction from a Single Image

  2023cited by this paper
• Generative Adversarial Networks

  2021cited by this paper
• Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regression

  2019influential reference
• GANs-based Clothes Design: Pattern Maker Is All You Need to Design Clothing

  2019cited by this paper
• Attention is All you Need

  2017cited by this paper
• Image-to-Image Translation with Conditional Adversarial Networks

  2016influential reference
• Conditional Generative Adversarial Nets

  2014cited by this paper

• No citing papers are available for this paper.