Garment Personalization via Identity Transfer

A new system provides a virtual experience akin to trying on clothing. It clones the user´s photographic image into a catalog of images of models wearing the desired garments. Simple offline training extracts the user´s head. Segmentation accurately separates the face, hair, and background, employing both a three-kernel statistical model and graph cuts. The system adjusts the resulting image´s skin color according to a statistical model and relights the head via spherical harmonics. Finally, using a parametric model, the system warps the clone´s body dimensions to fit the user´s dimensions. This creates high-quality compositions of the user´s image and the given garment.