Learning a Single Convolutional Super-Resolution Network for Multiple Degradations

View Researcher's Other Codes

MATLAB code for the following paper: “Learning a Single Convolutional Super-Resolution Network for Multiple Degradations”.

Disclaimer: The provided code links for this paper are external links. Science Nest has no responsibility for the accuracy, legality or content of these links. Also, by downloading this code(s), you agree to comply with the terms of use as set out by the author(s) of the code(s).

Please contact us in case of a broken link from here

Authors K. Zhang, W. Zuo, L. Zhang
Journal/Conference Name Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Paper Category
Paper Abstract Recent years have witnessed the unprecedented success of deep convolutional neural networks (CNNs) in single image super-resolution (SISR). However, existing CNN-based SISR methods mostly assume that a low-resolution (LR) image is bicubicly down sampled from a high-resolution (HR)image, thus inevitably giving rise to poor performance when the true degradation does not follow this assumption. More-over, they lack scalability in learning a single model to non-blindly deal with multiple degradations. To address these issues, we propose a general framework with dimensionality stretching strategy that enables a single convolutional super-resolution network to take two key factors of the SISR degradation process, i.e., blur kernel and noise level, as in-put. Consequently, the super-resolver can handle multiple and even spatially variant degradations, which significantly improves the practicability. Extensive experimental results on synthetic and real LR images show that the proposed convolutional super-resolution network not only can produce favorable results on multiple degradations but also is computationally efficient, providing a highly effective and scalable solution to practical SISR applications.
Date of publication 2018
Code Programming Language MATLAB

Copyright Researcher 2022