Multiple Cycle-in-Cycle Generative Adversarial Networks for Unsupervised Image Super-Resolution

With the help of convolutional neural networks (CNN), the single image super-resolution problem has been widely studied. Most of these CNN based methods focus on learning a model to map a low-resolution (LR) image to a high-resolution (HR) image, where the LR image is downsampled from the HR image with a known model. However, in a more general case when the process of the down-sampling is unknown and the LR input is degraded by noises and blurring, it is difficult to acquire the LR and HR image pairs for traditional supervised learning. Inspired by the recent unsupervised image-style translation applications using unpaired data, we propose a multiple Cycle-in-Cycle network structure to deal with the more general case using multiple generative adversarial networks (GAN) as the basis components. The first network cycle aims at mapping the noisy and blurry LR input to a noise-free LR space, then a new cycle with a well-trained <inline-formula> <tex-math notation="LaTeX">$\times 2$ </tex-math></inline-formula> network model is orderly introduced to super-resolve the intermediate output of the former cycle. The number of total cycles depends on the different up-sampling factors (<inline-formula> <tex-math notation="LaTeX">$\times 2$ </tex-math></inline-formula>, <inline-formula> <tex-math notation="LaTeX">$\times 4$ </tex-math></inline-formula>, <inline-formula> <tex-math notation="LaTeX">$\times 8$ </tex-math></inline-formula>). Finally, all modules are trained in an end-to-end manner to get the desired HR output. Quantitative indexes and qualitative results show that our proposed method achieves comparable performance with the state-of-the-art supervised models.