Image super-resolution, a state-of-the-art review and evaluation

Abstract

Image super-resolution is a popular technique for increasing the resolution of a given image. Its most common application is to provide better visual effect after resizing a digital image for display or printing. In recent years, due to consumer multimedia products being in vogue, imaging and display device become ubiquitous, and image super-resolution is becoming more and more important. There are mainly three categories of approaches for this problem: interpolation-based methods, reconstruction-based methods, and learning-based methods. This chapter is aimed, first, to explain the objective of image super-resolution, and then to describe the existing methods with special emphasis on color super-resolution. Finally, the performance of these methods is studied by carrying on objective and subjective image quality assessment on the super-resolution images.