A Survey of Super-Resolution Based on Deep Learning

Image super-resolution (SR) is an important low-level visual task in the field of image processing. It is used to enhance the resolution of images or videos and has a wide range of applications. In recent years, many researchers have begun to apply deep learning-based methods to SR task, which can significantly improve the quality of restored images. In this paper, we will introduce the concept of image super-resolution task, several typical CNNs based on supervised SR, unsupervised SR as well as the future research directions of SR.