In an industry where generative AI often produces isolated images, Style3D is pioneering a shift toward integrated product workflows. The company's latest research, GarmageNet, bridges the gap between 2D patterns and 3D garment forms, enabling AI to become a functional part of the design-to-production pipeline. This development is crucial as fashion brands seek to streamline operations and reduce time-to-market.
GarmageNet, developed by Style3D Research in collaboration with Zhejiang University, Shanghai Jiao Tong University, and Zhejiang Sci-Tech University, was published in ACM Transactions on Graphics and presented at SIGGRAPH Asia 2025. The framework addresses a central challenge: connecting 2D patterns with 3D garment geometry. It captures pattern outlines, 3D geometry, and sewing information in a unified representation, allowing inputs such as text, sketches, images, patterns, or point clouds to generate structured assets. By reconstructing sewing relationships and initializing physical simulation, GarmageNet enables design exploration, digital sampling, and editing—pushing AI beyond mere content generation into a connected product-development workflow.
The technology is backed 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 reported a 91.41% simulation-initialization success rate on 150 complex patterns, with an inference time of approximately eight seconds per garment under the study's test conditions. These metrics demonstrate the practical viability of AI-driven garment simulation.
Style3D's foundation in deformable-object simulation, garment deformation, digital fabrics, and AI-assisted workflows is evident in this research. The company maintains a substantial R&D organization and has published over 30 papers at conferences like SIGGRAPH, SIGGRAPH Asia, CVPR, NeurIPS, and 3DV. As of 28 July 2026, Style3D held 106 granted patents worldwide, including 58 invention patents and 12 granted in Europe and the United States, with 155 pending applications. It also operates an overseas R&D center in Germany, underscoring its global commitment to innovation.
The practical impact is already visible in industry adoption. 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 case illustrates the tangible benefits of integrated workflows, which are essential for brands aiming to remain competitive in a fast-paced market.
Style3D's approach extends beyond individual tools. As CEO Eric Liu told Just Style, "The most important development is the agent. We use agents to link different skills." The company 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. This vision positions AI as a collaborative partner rather than a replacement, ensuring that technology enhances human expertise.
In an era where fashion AI often remains siloed, Style3D's GarmageNet represents a significant step toward a more integrated future. By linking generative AI with structured product data and 3D technology, the company is not just creating images but enabling end-to-end digital product development. This shift could redefine how fashion teams approach design, sampling, and production, ultimately leading to more efficient and sustainable practices.
