3D Garments with Sewing Patterns

本数据集名为‘3D Garments with Sewing Patterns’，由韩国科学技术院文化技术研究生院创建。数据集包含超过23500种3D服装设计样本，涵盖19种不同的基础服装类型，旨在通过提供详细的缝制图案空间，促进神经3D服装建模和重建的研究。数据集的创建过程涉及使用灵活的描述结构定义参数化缝制图案模板，并通过自动生成管道生产3D服装模型，减少手动干预。该数据集特别适用于深度学习模型训练，以解决服装设计多样性和结构复杂性带来的挑战。

This dataset, named "3D Garments with Sewing Patterns", was developed by the Graduate School of Culture Technology at the Korea Advanced Institute of Science and Technology (KAIST). It contains over 23,500 3D garment design samples covering 19 distinct basic garment categories, and aims to facilitate research on neural 3D garment modeling and reconstruction by providing a detailed sewing pattern space. The dataset creation process involves defining parameterized sewing pattern templates with a flexible descriptive structure, and generating 3D garment models via an automated generation pipeline to reduce manual intervention. This dataset is particularly suitable for training deep learning models to address the challenges arising from the diversity and structural complexity of garment design.