Style3D, a technology company specializing in 3D and AI for the fashion industry, has introduced GarmageNet, a framework that connects generative AI with structured product data to enable connected workflows across design, development, content, and production. The announcement, made at SIGGRAPH Asia 2025 and published in ACM Transactions on Graphics, marks a shift from AI as a mere content generator to a tool integrated into the product lifecycle.
GarmageNet, developed by Style3D Research in collaboration with Zhejiang University, Shanghai Jiao Tong University, and Zhejiang Sci-Tech University, addresses a core challenge in fashion AI: linking 2D patterns with 3D garment forms. The framework captures pattern outlines, 3D geometry, and sewing information in a unified representation. It can accept inputs such as text, sketches, images, patterns, or point clouds, and generate structured assets, reconstruct sewing relationships, and initialize physical simulation. This enables design exploration, digital sampling, and editing, making AI a functional part of product development rather than an isolated image-generation tool.
GarmageNet's performance is notable. It is supported by GarmageSet, a dataset of 14,801 professionally created garments. In evaluations, GarmageJigsaw achieved 99.16% precision and 97.13% recall in sewing-point identification. GarmageNet achieved a 91.41% simulation-initialization success rate on 150 complex patterns, with an inference time of approximately eight seconds per garment under test conditions. These results suggest that the framework can handle real-world complexity, making it viable for industrial applications.
The research underscores Style3D's expertise in deformable-object simulation, garment deformation, digital fabrics, and AI-assisted workflows. The company has published over 30 papers at top conferences like SIGGRAPH, CVPR, and NeurIPS. As of July 2026, Style3D holds 106 granted patents worldwide, including 58 invention patents and 12 in Europe and the United States, with 155 more pending. It also operates an overseas R&D center in Germany.
Style3D's technologies are already in use by customers. 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. This demonstrates the practical impact of integrating AI and 3D into fashion workflows.
According to Style3D CEO Eric Liu, "The most important development is the agent. We use agents to link different skills." Style3D is advancing a connected fashion workflow where AI agents coordinate product data, 3D design, simulation, content creation, and production preparation, while human teams retain creative and operational responsibility.
For industry leaders, this development signals a move toward more efficient, data-driven fashion production. By enabling AI to handle complex tasks like pattern-to-3D mapping and simulation initialization, companies can reduce time-to-market and physical sampling, leading to cost savings and faster response to trends. The integration of AI into connected workflows could become a competitive advantage for early adopters.
As Style3D continues to innovate, the fashion industry may see a broader shift from traditional, siloed processes to integrated digital ecosystems. This could transform how garments are designed, developed, and produced, making AI an indispensable tool in the fashion supply chain.
