Learning Sewing Patterns via Latent Flow Matching of Implicit Fields

2026-01-25

AI Summary

Accurately modeling the geometric structure of garment sewing patterns and their seam relationships remains challenging. This work proposes a novel approach that, for the first time, combines implicit field representations with latent flow matching: signed or unsigned distance fields encode pattern boundaries and seam endpoints, enabling differentiable meshing within a continuous latent space, while a dedicated seam prediction module recovers stitching relationships between edge segments. The method outperforms existing techniques in the image-to-pattern inverse estimation task and further supports pattern completion and refitting, offering an efficient and high-precision practical tool for digital fashion design.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Search and Optimization: Learning to Search
• Machine Learning: Learning on the Edge & Model Compression

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Sewing patterns define the structural foundation of garments and are essential for applications such as fashion design, fabrication, and physical simulation. Despite progress in automated pattern generation, accurately modeling sewing patterns remains difficult due to the broad variability in panel geometry and seam arrangements. In this work, we introduce a sewing pattern modeling method based on an implicit representation. We represent each panel using a signed distance field that defines its boundary and an unsigned distance field that identifies seam endpoints, and encode these fields into a continuous latent space that enables differentiable meshing. A latent flow matching model learns distributions over panel combinations in this representation, and a stitching prediction module recovers seam relations from extracted edge segments. This formulation allows accurate modeling and generation of sewing patterns with complex structures. We further show that it can be used to estimate sewing patterns from images with improved accuracy relative to existing approaches, and supports applications such as pattern completion and refitting, providing a practical tool for digital fashion design.

Problem

• sewing patterns
• pattern generation
• garment modeling
• implicit fields
• digital fashion

Innovation

• implicit fields
• latent flow matching
• signed distance field
• sewing pattern generation
• differentiable meshing