GANHopper: Multi-Hop GAN for Unsupervised Image-to-Image Translation
This work addresses the problem of generating realistic intermediate images in unsupervised translation for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles unsupervised image-to-image translation by introducing GANHopper, which transforms images gradually through multiple hops using a hybrid discriminator and smoothness term, achieving improved performance in handling domain-specific features and geometric variations while preserving general color schemes.
We introduce GANHopper, 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 that resemble weighted hybrids between images from the 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. In addition to the standard cycle-consistency and adversarial losses, we introduce a new hybrid discriminator, which is trained to classify the intermediate images produced by the generator as weighted hybrids, with weights based on a predetermined hop count. We also add a smoothness term to constrain the magnitude of each hop, further regularizing the translation. Compared to previous methods, GANHopper excels at image translations involving domain-specific image features and geometric variations while also preserving non-domain-specific features such as general color schemes.