Single Image Super-Resolution via CNN Architectures and TV-TV Minimization

arXiv1907.05380MaRDI QIDQ6321950

Author name not available (Why is that?)

Publication date: 11 July 2019

Abstract: Super-resolution (SR) is a technique that allows increasing the resolution of a given image. Having applications in many areas, from medical imaging to consumer electronics, several SR methods have been proposed. Currently, the best performing methods are based on convolutional neural networks (CNNs) and require extensive datasets for training. However, at test time, they fail to impose consistency between the super-resolved image and the given low-resolution image, a property that classic reconstruction-based algorithms naturally enforce in spite of having poorer performance. Motivated by this observation, we propose a new framework that joins both approaches and produces images with superior quality than any of the prior methods. Although our framework requires additional computation, our experiments on Set5, Set14, and BSD100 show that it systematically produces images with better peak signal to noise ratio (PSNR) and structural similarity (SSIM) than the current state-of-the-art CNN architectures for SR.

Has companion code repository: https://github.com/marijavella/sr-tvtvsolver

This page was built for publication: Single Image Super-Resolution via CNN Architectures and TV-TV Minimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6321950)