Cyclical opposing generation network for unsupervised cross-domain image generation

摘要

A system for unsupervised cross-domain image generation relative to a first and a second image domain, each of which comprises real images, is created. A first generator generates synthetic images that are similar to real images in the second domain, while comprising semantic content of real images in the first domain. A second generator generates synthetic images that are similar to real images in the first domain, while comprising semantic content of real images in the second domain. A first discriminator distinguishes real images in the first domain from synthetic images generated by the second generator. A second discriminator distinguishes real images in the second domain from synthetic images generated by the first generator. The discriminators and generators are deep neural networks and each form a generation network and a discrimination network in a cyclic GAN framework that is configured to increase an error rate of the discrimination network in order to improve the quality of the synthetic images.