Automatic pose and wrinkle transfer for aesthetic garment display

We present an automatic and semantic pose and wrinkle transfer method from one garment onto another for aesthetic display, which is previously performed by professional artists using a knowledge-intensive and time-consuming process. Given a source garment model with fine wrinkle details in a specific pose and another target garment model with a similar style in a neutral pose but without fine wrinkle details, our approach can automatically transfer the pose and wrinkle details faithfully from the source to the target using a two-stage process. In the semantic correspondence establishment stage, we construct a dense correspondence between the source and the target by utilizing their semantic information in 2D patterns. Specifically, we first obtain the initial correspondence points on the paired 2D patterns by leveraging their semantic information. These marker points, which act as constraints, are mapped to their corresponding 3D models. We then establish their per-triangle correspondence using a non-rigid Iterative Closest Point (ICP) algorithm. In the deformation transfer stage, we transfer the pose and wrinkle details from the source to the target by solving an optimization problem. Extensive experiments validate that our method is able to generate better results compared to state-of-the-art methods, and it can lead to significant time savings for fashion designers. •A novel automatic and semantic deformation transfer framework designed for aesthetic online garment display in e-commerce.•It can faithfully transfer the fine-grained pose and wrinkle details of high-resolution source models to target models.•A semantic correspondence establishment strategy to automatically align the source and target models.•A 3D high-quality garment dataset consisting of 18 paired models of various types.