XGAN: Unsupervised Image-to-Image Translation for many-to-many Mappings
arXiv: Computer Vision and Pattern Recognition, Volume abs/1711.05139, 2018, Pages 33-49.
We introduced XGAN, a model for unsupervised domain translation applied to the task of semantically-consistent style transfer
Style transfer usually refers to the task of applying color and texture information from a specific style image to a given content image while preserving the structure of the latter. Here we tackle the more generic problem of semantic style transfer: given two unpaired collections of images, we aim to learn a mapping between the corpus-le...More
PPT (Upload PPT)