I. Introduction
As one of the most critical tasks in computer vision, image Super-Resolution (SR) plays a prominent role in numerous fields such as satellite imaging [1], medical imaging [2], face recognition [3], video surveillance [4], and hyperspectral imaging [5] due to its ability to reconstruct High-Resolution (HR) images with rich details from the corresponding Low-Resolution (LR) images. In recent years, Convolutional Neural Network (CNN) [6], [7], [8], [9], [10], [11], [12], [13] has shown remarkable performance in the SR task.