Image super-resolution, which is used to restore high-resolution image from a single low-resolution (LR) image, is a difficult challenging problem in computer field. In recent times, dominant deep learning algorithms have been applied to Single image superresolution and have shown a highly efficient performance.SR methods are usually based on two important algorithms: high quality spatial (in-frame) up-scaling, and motion compensation for finding corresponding areas in neighbour frames. The aim is to understand in a better manner, the application of super-resolution images in the future by understanding how things work in the digital world.