Content area
Abstract
A new approach for 2D to 3D garment retexturing is proposed based on Gaussian mixture models and thin plate splines (TPS). An automatically segmented garment of an individual is matched to a new source garment and rendered, resulting in augmented images in which the target garment has been retextured using the texture of the source garment. We divide the problem into garment boundary matching based on Gaussian mixture models and then interpolate inner points using surface topology extracted through geodesic paths, which leads to a more realistic result than standard approaches. We evaluated and compared our system quantitatively by root mean square error (RMS) and qualitatively using the mean opinion score (MOS), showing the benefits of the proposed methodology on our gathered dataset.
Details
1 iCV Research Group, Institute of Technology, University of Tartu, Tartu, Estonia
2 Computer Vision Center and Universitat Autònoma de Barcelona, Catalonia, Spain
3 Computer Vision Center and University of Barcelona, Catalonia, Spain
4 Computer Vision Center and Universitat Oberta de Catalunya, Catalonia, Spain
5 Find Fashion, Tartu, Estonia
6 iCV Research Group, Institute of Technology, University of Tartu, Tartu, Estonia; Department of Electrical and Electronics Engineering, Hasan Kalyoncu University, Gaziantep, Turkey; Institute for Digital Technologies, Loughborough University, London, UK