In many applications such as, image assisted surgery and video surveillance, availability of high-quality high-resolution images is crucial. However, the existing image capturing devices are generally not equipped to capture such images. Therefore, development of high-performance super resolution algorithms is extremely important to the image processing community. Initially, the image super resolution schemes in the literature were developed by formulating the problem of image super resolution solely as an optimization problem and solving it using efficient numerical techniques. In recent years, the emergence of artificial intelligence and convolutional neural networks has provided impetus to developing many high-performance architectures for super resolution. In this paper, we first start formulating the image super resolution as a three-prior optimization problem, in which each of the three priors models a realistic step in the super resolution task. Then, the solution of the optimiz...

The task of image super resolution is crucial in many applications, such as computer vision and medical imaging. Conventionally, the task of image super resolution was carried out by formulating it as a constrained optimization problem and then solving it using suitable numerical techniques. However, after the emergence of deep neural networks, the focus of the researchers in this area has been almost entirely on designing deep convolutional neural network architectures that indeed have provided remarkable performance for the task of image super resolution. Even though unified methods of combining the two approaches has a greater potential of providing a superior performance for the task of image super resolution, with the exception of very few works, not much attention has been paid to develop such a unified method for this task. In this article, we propose a three-prior formulation of the optimization problem for image super resolution and develop an ultralight-weight convolutional n...