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

TL;DR

This paper introduces SR2*GAN, a deep residual StarGAN-based model capable of handling multi-domain image super-resolution with a single network, improving performance across various degradation types.

Contribution

The paper presents a novel multi-domain super-resolution method using a StarGAN-like architecture, enabling a single model to super-resolve images from different degradation domains.

Findings

Effective in handling multiple degradation types

Outperforms state-of-the-art methods in experiments

Scalable and efficient for real-world applications

Abstract

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 (SR2*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.