Single-Image Super-Resolution via Multiple Matrix-Valued Kernel Regression
- 1 July 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
Abstract
Single-image super-resolution focuses on learning a mapping to recover high-resolution images from given low-resolution images with the help of a set of paired images. Matrix-valued operators serve as an efficient mapping to super-resolve low-resolution images. However, most existed matrix-valued based super-resolution algorithms limit matrix-valued operators as linear mappings. Multiple matrix-valued operators based algorithm is introduced for improving the performance of matrix-value operators in single-image super-resolution. Taking advantages of the non-linear style of multiple matrix-valued operators, we have more accurate super-resolved images. The experimental results show the efficiency and effectiveness of the reported multiple matrix-valued operator learning based super-resolution algorithm.Keywords
This publication has 19 references indexed in Scilit:
- Piece-Wise Kernel Regression for Example-Based Super-Resolution2018
- Learning local dictionaries and similarity structures for single image super-resolutionSignal Processing, 2018
- Example-based super-resolution via social imagesNeurocomputing, 2016
- Deep learning in neural networks: An overviewNeural Networks, 2015
- Matrix-value regression for single-image super-resolution2013
- Single-image super-resolution via local learningInternational Journal of Machine Learning and Cybernetics, 2011
- Super-resolution through neighbor embedding2004
- Kernel Methods for Pattern Analysis2004
- Example-based super-resolutionIEEE Computer Graphics and Applications, 2002
- Learning Low-Level VisionInternational Journal of Computer Vision, 2000