pith. sign in

arxiv: 1805.03383 · v2 · pith:DFDGSG3Inew · submitted 2018-05-09 · 💻 cs.CV

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

classification 💻 cs.CV
keywords entryplacestructuresuper-resolutiontrackchallengesdenoisingrealistic
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.