A 3D Shape Mapping Method Using Eigenspace Clustering Applied on Virtual Clothing

Virtual clothing try-on can be a great option for the online clothing industry. In this paper, we propose a method to map the 3D model of selected clothes on the customer's 3D model. For this purpose, the point clouds of the customer and mannequin are captured by the Kinect camera. These models are segmented into corresponding parts using surface descriptors to ease the matching. Then, individual parts of the mannequin are mapped on the corresponding parts of the customer. Finally, the color information from the clothes on the mannequin is transformed to the customer's body point cloud. The proposed method has two main advantages over the existing methods. First, no need for an expert to design 3D models in graphic software. Second, any style and texture of clothes can be chosen by the customer. The results of the experiments show the ability of the proposed method compared to existing methods.