GANHopper: Multi-Hop GAN for Unsupervised Image-to-Image Translation
arXiv:2002.10102
Abstract
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.
arXiv commentTo be presented at ECCV 2020. Code is available at https://github.com/wallacemplira/ganhopper
References in corpus (13)
- Rethinking Atrous Convolution for Semantic Image Segmentation
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Toward Multimodal Image-to-Image Translation
- Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
- Unsupervised Image-to-Image Translation Networks
- Multimodal Unsupervised Image-to-Image Translation
- Fader Networks: Manipulating Images by Sliding Attributes
- CariGANs: Unpaired Photo-to-Caricature Translation
- Deep Learning Face Attributes in the Wild
- InstaGAN: Instance-aware Image-to-Image Translation
- LOGAN: Unpaired Shape Transform in Latent Overcomplete Space
- Large-Scale Deep Learning on the YFCC100M Dataset
- Cross-Domain Cascaded Deep Feature Translation