New techniques for preserving global structure and denoising with low information loss in single-image super-resolution
Conference Paper
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.
Full Text
Duke Authors
Cited Authors
- Bei, Y; Damian, A; Hu, S; Menon, S; Ravi, N; Rudin, C
Published Date
- December 13, 2018
Published In
Volume / Issue
- 2018-June /
Start / End Page
- 987 - 994
Electronic International Standard Serial Number (EISSN)
- 2160-7516
International Standard Serial Number (ISSN)
- 2160-7508
International Standard Book Number 13 (ISBN-13)
- 9781538661000
Digital Object Identifier (DOI)
- 10.1109/CVPRW.2018.00132
Citation Source
- Scopus