Learning Sewing Patterns via Latent Flow Matching of Implicit Fields

TL;DR

This paper introduces a novel implicit representation-based method for modeling and generating complex sewing patterns, improving accuracy in pattern estimation and enabling applications like completion and refitting.

Contribution

It proposes a continuous latent space encoding of sewing patterns using signed and unsigned distance fields, facilitating differentiable meshing and pattern generation.

Findings

Accurately models complex sewing patterns with implicit fields.

Improves sewing pattern estimation from images.

Supports pattern completion and refitting tasks.

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.