AutoSew: A Geometric Approach to Stitching Prediction with Graph Neural Networks

TL;DR

This work presents AutoSew, a fully automatic, geometry-based approach for predicting stitch correspondences directly from 2D pattern contours, enabling scalable garment assembly without manual input.

Abstract

Automating garment assembly from sewing patterns remains a significant challenge due to the lack of standardized annotation protocols and the frequent absence of semantic cues. Existing methods often rely on panel labels or handcrafted heuristics, which limit their applicability to real-world, non-conforming patterns. We present AutoSew, a fully automatic, geometry-based approach for predicting stitch correspondences directly from 2D pattern contours. AutoSew formulates the problem as a graph matching task, leveraging a Graph Neural Network to capture local and global geometric context, and employing a differentiable optimal transport solver to infer stitching relationships-including multi-edge connections. To support this task, we update the GarmentCodeData dataset modifying over 18k patterns with realistic multi-edge annotations, reflecting industrial assembly scenarios. AutoSew achieves 96% F1-score and successfully assembles 73.3% of test garments without error, outperforming existing methods while relying solely on geometric input. Our results demonstrate that geometry alone can robustly guide stitching prediction, enabling scalable garment assembly without manual input.

Figures (5)

• Figure 1: Left: AutoSew takes as input a 2D sewing pattern, consisting of the contours of the panels (24 in this example) and outputs the edges that should be stitched together to assemble the garment. Middle: Our method models the stitching edges as a graph neural network and leverages feature aggregation with an adaptive matching mechanism to efficiently solve a partial assignment problem. Multi-edge stitching connections are shown in green, while one-to-one stitches are in blue. Right: 3D garment assembled from the resulting stitching connections predicted by our model.
• Figure 2: Overview of AutoSew. For each sewing pattern, a graph is constructed with nodes representing stitching edges and edges capturing geometric relationships of the panels. A GNN with message passing learns embeddings for each edge, optimized for stitch correspondence using a differentiable optimal transport loss.
• Figure 3: Comparison of sewing patterns and draped avatars before and after multi-edge merging. Top: original dataset with one-to-one stitches, showing artificial seam marks. Bottom: our Multi-Edge dataset with realistic multi-to-one stitches, producing more natural seams and garment reconstructions.
• Figure 4: Random results showcasing actual patterns from the M-E.GarmentCodeData.
• Figure 5: Impact of confidence threshold on AutoSew's stitching prediction performance.