A Deep Residual Star Generative Adversarial Network for multi-domain Image Super-Resolution
This addresses the inefficiency of existing super-resolution methods in real-world scenarios where degradation processes are unknown, though it is incremental as it builds on StarGAN-like topologies.
The paper tackles the problem of single image super-resolution under multiple unknown degradation settings, proposing a deep Super-Resolution Residual StarGAN (SR2*GAN) that handles multiple low-resolution domains with a single model, demonstrating effectiveness in quantitative and qualitative experiments.
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.