UNPAIRED IMAGE-TO-IMAGE SHAPE TRANSLATION ACROSS FASHION DATA

We address the problem of unsupervised geometric image- to-image translation. Rather than transferring the style of an image as a whole, our goal is to translate the geometry of an object as depicted in different domains while preserving its appearance characteristics. Our model is trained in an unsupervised fashion, i.e. without the need of paired images during training. It performs all steps of the shape transfer within a single model and without additional post-processing stages. Extensive experiments on the VITON and our own Fashion- Style dataset show the effectiveness of the method.