Seven Ways to Improve Example-Based Single Image Super Resolution
Abstract
In this paper we present seven techniques that everybody should know to improve example-based single image super resolution (SR): 1) augmentation of data, 2) use of large dictionaries with efficient search structures, 3) cascading, 4) image self-similarities, 5) back projection refinement, 6) enhanced prediction by consistency check, and 7) context reasoning. We validate our seven techniques on standard SR benchmarks (i.e. Set5, Set14, B100) and methods (i.e. A+, SRCNN, ANR, Zeyde, Yang) and achieve substantial improvements.The techniques are widely applicable and require no changes or only minor adjustments of the SR methods. Moreover, our Improved A+ (IA) method sets new state-of-the-art results outperforming A+ by up to 0.9dB on average PSNR whilst maintaining a low time complexity.
Cite
Text
Timofte et al. "Seven Ways to Improve Example-Based Single Image Super Resolution." Conference on Computer Vision and Pattern Recognition, 2016. doi:10.1109/CVPR.2016.206Markdown
[Timofte et al. "Seven Ways to Improve Example-Based Single Image Super Resolution." Conference on Computer Vision and Pattern Recognition, 2016.](https://mlanthology.org/cvpr/2016/timofte2016cvpr-seven/) doi:10.1109/CVPR.2016.206BibTeX
@inproceedings{timofte2016cvpr-seven,
title = {{Seven Ways to Improve Example-Based Single Image Super Resolution}},
author = {Timofte, Radu and Rothe, Rasmus and Van Gool, Luc},
booktitle = {Conference on Computer Vision and Pattern Recognition},
year = {2016},
doi = {10.1109/CVPR.2016.206},
url = {https://mlanthology.org/cvpr/2016/timofte2016cvpr-seven/}
}