GarmentCodeData: A Dataset of 3D Made-to-Measure Garments With Sewing Patterns

TL;DR

This paper introduces GarmentCodeData, a large-scale synthetic dataset of 3D garments with sewing patterns, generated through an automated pipeline, to support research in virtual fitting and garment reconstruction.

Contribution

It provides the first extensive synthetic dataset of 3D garments with sewing patterns and a novel automated generation pipeline for scalable dataset creation.

Findings

Contains 115,000 data points across various garment types.

Includes algorithms for automatic measurement and sewing pattern sampling.

Features an open-source 3D draping pipeline with collision resolution.

Abstract

Recent research interest in the learning-based processing of garments, from virtual fitting to generation and reconstruction, stumbles on a scarcity of high-quality public data in the domain. We contribute to resolving this need by presenting the first large-scale synthetic dataset of 3D made-to-measure garments with sewing patterns, as well as its generation pipeline. GarmentCodeData contains 115,000 data points that cover a variety of designs in many common garment categories: tops, shirts, dresses, jumpsuits, skirts, pants, etc., fitted to a variety of body shapes sampled from a custom statistical body model based on CAESAR, as well as a standard reference body shape, applying three different textile materials. To enable the creation of datasets of such complexity, we introduce a set of algorithms for automatically taking tailor's measures on sampled body shapes, sampling strategies for sewing pattern design, and propose an automatic, open-source 3D garment draping pipeline based on a fast XPBD simulator, while contributing several solutions for collision resolution and drape correctness to enable scalability. Project Page: https://igl.ethz.ch/projects/GarmentCodeData/