Learning-based Seam Correspondence Reconstruction in Sewing Patterns
This work automates a labor-intensive step in 3D garment modeling from sewing patterns, benefiting digital fashion and animation industries.
The paper presents a graph-based learning framework that reconstructs coarse panel connectivity and fine-grained seam correspondences from 2D sewing pattern geometry, achieving high stitching accuracy and strong generalization across garment styles.
Digital sewing patterns typically consist of disjoint 2D panels without explicit stitch annotations, making downstream 3D modeling reliant on labor-intensive expert specification. In this paper, we present a graph-based learning framework that reconstructs two-level stitching information, coarse panel connectivity and fine-grained seam correspondence, from 2D panel geometry alone. At the coarse level, panel connectivity is inferred by predicting panel semantics associated with anatomical body regions, enforcing consistency with body structure and garment design conventions. Based on the reconstructed panel graph, fine-grained seam correspondences between panel pairs are inferred by learning latent edge representations that jointly encode local seam geometry and global garment context through graph message passing. The resulting edge embeddings are subsequently decoded into detailed seam correspondences. Our method supports complex sewing-pattern topologies, including many-to-one correspondences, intra-panel seams, and curved seams. Experiments demonstrate high stitching accuracy and strong generalization across garment styles.