CrossNet: Latent Cross-Consistency for Unpaired Image Translation

Omry Sendik, Dani Lischinski, Daniel Cohen-Or
2020 2020 IEEE Winter Conference on Applications of Computer Vision (WACV)  
Figure 1 : Given two unpaired sets of images, we train a model to perform translation between the two sets. Here we show, from left to right, our results on changing a specular material to diffuse, enhancing a mobile phone image to look like one taken by a Digital SLR camera and foreground extraction. Abstract Recent GAN-based architectures have been able to deliver impressive performance on the general task of imageto-image translation. In particular, it was shown that a wide variety of image
more » ... ranslation operators may be learned from two image sets, containing images from two different domains, without establishing an explicit pairing between the images. This was made possible by introducing clever regularizers to overcome the under-constrained nature of the unpaired translation problem. In this work, we introduce a novel architecture for unpaired image translation, and explore several new regularizers enabled by it. Specifically, our architecture comprises a pair of GANs, as well as a pair of translators between their respective latent spaces. These cross-translators enable us to impose several regularizing constraints on the learnt image translation operator, collectively referred to as latent cross-consistency. Our results show that our proposed architecture and latent cross-consistency constraints are able to outperform the existing state-of-the-art on a variety of image translation tasks.
doi:10.1109/wacv45572.2020.9093322 dblp:conf/wacv/SendikLC20 fatcat:ehdntjb3v5e2xmwydg4kxaajzm