A Deep Residual Star Generative Adversarial Network for multi-domain Image Super-Resolution

Recently, most of state-of-the-art single image super-resolution (SISR) methods have attained impressive performance by using deep convolutional neural networks (DCNNs). The existing SR methods have limited performance due to a fixed degradation settings, i.e. usually a bicubic downscaling of low-resolution (LR) image. However, in real-world settings, the LR degradation process is unknown which can be bicubic LR, bilinear LR, nearest-neighbor LR, or real LR. Therefore, most SR methods are ineffective and inefficient in handling more than one degradation settings within a single network. To handle the multiple degradation, i.e. refers to multi-domain image super-resolution, we propose a deep Super-Resolution Residual StarGAN (SR^2*GAN), a novel and scalable approach that super-resolves the LR images for the multiple LR domains using only a single model. The proposed scheme is trained in a StarGAN like network topology with a single generator and discriminator networks. We demonstrate the effectiveness of our proposed approach in quantitative and qualitative experiments compared to other state-of-the-art methods.

I. Introduction

The goal of the single image super-resolution (SISR) is to reconstruct the high-resolution (HR) image from its low-resolution (LR) image counterpart. SISR problem is a fundamental low-level vision and image processing problem with various practical applications in satellite imaging, medical imaging, video enhancement and security and surveillance imaging as well. With the increasing amount of HR images / videos data on the internet, there is a great demand for storing, transferring, and sharing such large sized data with low cost of storage and bandwidth resources. Moreover, the HR images are usually downscaled to easily fit into display screens with different resolutions while retaining visually plausible information. The downscaled LR counterpart of the HR can efficiently utilize lower bandwidth, save storage, and easily fit to various digital displays. However, some details are lost and sometimes visible artifacts appear when users downscale and upscale the digital contents.