AutoSew: A Geometric Approach to Stitching Prediction with Graph Neural Networks
This addresses the problem of scalable garment assembly for manufacturing/design, though it appears incremental as it builds on existing geometric approaches with improved methods.
The paper tackles the challenge of automating garment assembly from sewing patterns by developing AutoSew, a geometry-based approach that predicts stitch correspondences directly from 2D pattern contours using graph neural networks and optimal transport. It achieves 96% F1-score and successfully assembles 73.3% of test garments without error.
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.