The Super-Resolution Generative Adversarial Network (SRGAN) is a seminal work that is capable of generating realistic textures during single image super-resolution. However, the hallucinated details are often accompanied with unpleasant artifacts. To further enhance the visual quality, we thoroughly study three key components of SRGAN - network architecture, adversarial loss and perceptual loss, and improve each of them to derive an Enhanced SRGAN (ESRGAN). In particular, we introduce the Residual-in-Residual Dense Block (RRDB) without batch normalization as the basic network building unit. Moreover, we borrow the idea from relativistic GAN to let the discriminator predict relative realness instead of the absolute value. Finally, we improve the perceptual loss by using the features before activation, which could provide stronger supervision for brightness consistency and texture recovery. Benefiting from these improvements, the proposed ESRGAN achieves consistently better visual quality with more realistic and natural textures than SRGAN and won the first place in the PIRM2018-SR Challenge. The code is available at https://github.com/xinntao/ESRGAN .

Blind image super-resolution (SR), aiming to super-resolve low-resolution images with unknown degradation, has attracted increasing attention due to its significance in promoting real-world applications. Many novel and effective solutions have been proposed recently, especially with powerful deep learning techniques. Despite years of efforts, it still remains as a challenging research problem. This paper serves as a systematic review on recent progress in blind image SR, and proposes a taxonomy to categorize existing methods into three different classes according to their ways of degradation modelling and the data used to solve the SR model. This taxonomy helps summarize and distinguish among existing methods. We hope to provide insights into current research states, as well as revealing novel research directions worth exploring. In addition, we make a summary on commonly used datasets and previous competitions related to blind image SR. Last but not least, a comparison among different methods is provided with detailed analysis on their merits and demerits using both synthetic and real testing images.

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 highresolution (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 imagestyle 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 ×2 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 (×2, ×4, ×8). 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.

Transformer-based methods have shown impressive performance in image restoration tasks, such as image super-resolution and denoising. However, we find that these networks can only utilize a limited spatial range of input information through attribution analysis. This implies that the potential of Transformer is still not fully exploited in existing networks. In order to activate more input pixels for better restoration, we propose a new Hybrid Attention Transformer (HAT). It combines both channel attention and window-based self-attention schemes, thus making use of their complementary advantages. Moreover, to better aggregate the cross-window information, we introduce an overlapping cross-attention module to enhance the interaction between neighboring window features. In the training stage, we additionally adopt a same-task pre-training strategy to further exploit the potential of the model for further improvement. Extensive experiments have demonstrated the effectiveness of the proposed modules. We further scale up the model to show that the performance of the SR task can be greatly improved. Besides, we extend HAT to more image restoration applications, including real-world image super-resolution, Gaussian image denoising and image compression artifacts reduction. Experiments on benchmark and real-world datasets demonstrate that our HAT achieves state-of-the-art performance both quantitatively and qualitatively.