Robust Single-Image Super-Resolution via CNNs and TV-TV Minimization

arXiv2004.00843MaRDI QIDQ6337906FDOQ6337906

Authors: Marija Vella, João F. C. Mota 

Publication date: 2 April 2020

Abstract: Single-image super-resolution is the process of increasing the resolution of an image, obtaining a high-resolution (HR) image from a low-resolution (LR) one. By leveraging large training datasets, convolutional neural networks (CNNs) currently achieve the state-of-the-art performance in this task. Yet, during testing/deployment, they fail to enforce consistency between the HR and LR images: if we downsample the output HR image, it never matches its LR input. Based on this observation, we propose to post-process the CNN outputs with an optimization problem that we call TV-TV minimization, which enforces consistency. As our extensive experiments show, such post-processing not only improves the quality of the images, in terms of PSNR and SSIM, but also makes the super-resolution task robust to operator mismatch, i.e., when the true downsampling operator is different from the one used to create the training dataset.

Has companion code repository: https://github.com/marijavella/sr-via-CNNs-and-tvtv

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

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6337906)