MeshTailor: Cutting Seams via Generative Mesh Traversal
This work addresses the problem of automatic seam generation for 3D mesh parameterization, offering a projection-free, edge-aligned approach that eliminates artifacts from existing methods.
MeshTailor introduces the first mesh-native generative framework for synthesizing edge-aligned seams on 3D surfaces, outperforming prior optimization-based and learning-based methods in producing coherent, professional-quality seam layouts.
We present MeshTailor, the first mesh-native generative framework for synthesizing edge-aligned seams on 3D surfaces. Unlike prior optimization-based or extrinsic learning-based methods, MeshTailor operates directly on the mesh graph, eliminating projection artifacts and fragile snapping heuristics. We introduce ChainingSeams, a hierarchical serialization of the seam graph that prioritizes global structural cuts before local details in a coarse-to-fine manner, and a dual-stream encoder that fuses topological and geometric context. Leveraging this hierarchical representation and enriched vertex embeddings, our MeshTailor Transformer utilizes an autoregressive pointer layer to trace seams vertex-by-vertex within local neighborhoods, ensuring projection-free, edge-aligned seams. Extensive evaluations show that MeshTailor produces more coherent, professional-quality seam layouts compared to recent optimization-based and learning-based baselines.