ECCV 2020 paper: "GANHopper: Multi-Hop GAN for Unsupervised Image-to-Image Translation"

An unsupervised image-to-image translation network that transforms images gradually between two domains, through multiple hops. Instead of executing translation directly, we steer the translation by requiring the network to produce in-between images which resemble weighted hybrids between images from the two input domains. Our network is trained on unpaired images from the two domains only, without any in-between images. All hops are produced using a single generator along each direction.

GANHopper excels at learning translations that involve shape domain-specific image features and geometric variations (e.g., dogs to cats) while also preserving non-domain-specific features such as general color schemes.

Видео ECCV 2020 paper: "GANHopper: Multi-Hop GAN for Unsupervised Image-to-Image Translation" канала Hao Zhang