Generative adversarial networks- and ResNets-based framework for image translation with super-resolution

Abstract

Recent research on image translation has great progress with the development of generative adversarial networks (GANs) techniques. Generating high-resolution images with unsupervised architecture is one of the most challenging tasks for image translation. To this end, we propose an enhanced super-resolution generative adversarial network for image translation. First, for unlabeled datasets, we employ reconstructed consistency loss and mutual dual GANs, which contains two generators:GA → B, GB → A and two discriminators: DB, DA to develop an unsupervised learning framework. As reconstructed consistency loss is added between generators of GA → B and GB → A, our designed overall architecture can learn mapping function of different domains even without unpaired samples. In addition, the generator network includes encoder network, decoder network, and residual network with skip connections to generate high-resolution images with realistic details. Meanwhile, a stable normalization is proposed to stabilize the training of our discriminator networks. Finally, experimental results are carried out on six different datasets, demonstrating that our algorithms outperform the state-of-the-art methods in terms of the image quality and image resolution.