New Techniques for Preserving Global Structure and Denoising With Low Information Loss in Single-Image Super-Resolution

Yijie Bei, Alexandru Damian, Shijia Hu, Sachit Menon, Nikhil Ravi, Cynthia Rudin; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2018, pp. 874-881

Abstract


This work identifies and addresses two important technical challenges in single-image super-resolution: (1) how to upsample an image without magnifying noise and (2) how to preserve large scale structure when upsampling. We summarize the techniques we developed for our second place entry in Track 1 (Bicubic Downsampling), seventh place entry in Track 2 (Realistic Adverse Conditions), and seventh place entry in Track 3 (Realistic difficult) in the 2018 NTIRE Super-Resolution Challenge. Furthermore, we present new neural network architectures that specifically address the two challenges listed above: denoising and preservation of large-scale structure.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Bei_2018_CVPR_Workshops,
author = {Bei, Yijie and Damian, Alexandru and Hu, Shijia and Menon, Sachit and Ravi, Nikhil and Rudin, Cynthia},
title = {New Techniques for Preserving Global Structure and Denoising With Low Information Loss in Single-Image Super-Resolution},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2018}
}