DressWild: Feed-Forward Pose-Agnostic Garment Sewing Pattern Generation from In-the-Wild Images
We reconstruct simulation-ready sewing patterns and 3D garments from a single in-the-wild image. A feed-forward pipeline uses vision-language models to handle diverse poses and viewpoints without iterative optimization.
Dec 6, 2026
Design2GarmentCode: Turning Design Concepts to Tangible Garments Through Program Synthesis
We propose a sewing pattern generation approach based on Large Multimodal Models, to generate parametric pattern-making programs from multi-modal design concepts.
Jun 11, 2025