Style3D, a technology company specializing in fashion AI and 3D solutions, is advancing the integration of generative AI with structured product data to create connected workflows for fashion design and production. The company recently showcased its research at SIGGRAPH Asia 2025, highlighting a new framework called GarmageNet that aims to bridge the gap between 2D patterns and 3D garment forms.
Developed in collaboration with Zhejiang University, Shanghai Jiao Tong University, and Zhejiang Sci-Tech University, GarmageNet addresses a central challenge in fashion AI: connecting 2D patterns with 3D garment forms. The framework captures pattern outlines, 3D geometry, and sewing information in a unified representation. It can use text, sketches, images, patterns, or point clouds as inputs, then generate structured assets, reconstruct sewing relationships, and initialize physical simulation for design exploration, digital sampling, and editing.
By linking inputs with patterns, sewing relationships, and simulation, GarmageNet illustrates how fashion AI can become part of a connected product-development workflow rather than remain an isolated image-generation tool. The research is supported by GarmageSet, a dataset of 14,801 professionally created garments. In evaluations, GarmageNet achieved a 91.41% simulation-initialization success rate on 150 complex patterns, with an inference time of approximately eight seconds per garment.
The implications for the fashion industry are significant. Traditional fashion design and development often involves disjointed processes, with 2D patterns, 3D samples, and production data managed separately. Style3D's approach aims to unify these elements, enabling faster iteration and reducing reliance on physical samples. For example, German menswear brand OLYMP uses Style3D and Assyst to connect 2D patterns, 3D simulation, visualization, and digital showrooms. The company reports developing styles in days rather than weeks, reducing physical samples and improving communication across design, sales, and production.
Style3D's CEO Eric Liu emphasized the role of AI agents in this transformation, stating, "The most important development is the agent. We use agents to link different skills." Style3D is advancing a connected fashion workflow in which AI agents can coordinate product data, 3D design, simulation, content creation, and production preparation—while human teams retain creative and operational responsibility.
The company's research foundation is strong, with more than 30 papers published at conferences including SIGGRAPH, SIGGRAPH Asia, CVPR, NeurIPS, and 3DV. As of 28 July 2026, Style3D held 106 granted patents worldwide, including 58 invention patents, and operates an overseas R&D center in Germany. This positions Style3D as a key player in the evolving landscape of fashion technology, where AI and 3D are reshaping how garments are designed, developed, and brought to market.
For fashion companies, adopting such technologies could mean significant gains in efficiency and sustainability. By connecting design and production data, brands can reduce waste from physical sampling and accelerate time-to-market. As the industry increasingly embraces digital transformation, tools like GarmageNet could become essential for staying competitive.
