Deep Cyclic Generative Adversarial Residual Convolutional Networks for Real Image Super-Resolution
This addresses the challenge of applying super-resolution to real images with unknown degradation, which is important for mobile and embedded devices, though it is incremental as it builds on existing CycleGAN and GAN frameworks.
The paper tackles the problem of real-world single image super-resolution by proposing a deep cyclic generative adversarial network that maintains domain consistency between low- and high-resolution images, achieving results comparable to state-of-the-art methods on benchmark datasets.
Recent deep learning based single image super-resolution (SISR) methods mostly train their models in a clean data domain where the low-resolution (LR) and the high-resolution (HR) images come from noise-free settings (same domain) due to the bicubic down-sampling assumption. However, such degradation process is not available in real-world settings. We consider a deep cyclic network structure to maintain the domain consistency between the LR and HR data distributions, which is inspired by the recent success of CycleGAN in the image-to-image translation applications. We propose the Super-Resolution Residual Cyclic Generative Adversarial Network (SRResCycGAN) by training with a generative adversarial network (GAN) framework for the LR to HR domain translation in an end-to-end manner. We demonstrate our proposed approach in the quantitative and qualitative experiments that generalize well to the real image super-resolution and it is easy to deploy for the mobile/embedded devices. In addition, our SR results on the AIM 2020 Real Image SR Challenge datasets demonstrate that the proposed SR approach achieves comparable results as the other state-of-art methods.