Style3D introduces GarmageNet to bridge 2D patterns and 3D fashion workflows

Style3D has introduced GarmageNet, a new framework designed to bridge the gap between 2D patterns and 3D garment forms in fashion production. Developed by Style3D Research in collaboration with Zhejiang University, Shanghai Jiao Tong University, and Zhejiang Sci-Tech University, the technology aims to transform generative AI from a simple image-generation tool into a connected workflow for design, development, and production.

GarmageNet captures pattern outlines, 3D geometry, and sewing information within a unified representation. It can process various inputs—including text, sketches, images, patterns, or point clouds—to generate structured assets, reconstruct sewing relationships, and initialize physical simulations. This allows for more efficient digital sampling and design exploration.

The framework is supported by GarmageSet, a dataset containing 14,801 professionally created garments. In technical evaluations, the GarmageJigsaw component achieved 99.16% precision and 97.13% recall in identifying sewing points. Additionally, GarmageNet reached a 91.41% success rate for simulation initialization on complex patterns, with an inference time of approximately eight seconds per garment.