Unsupervised Single-Image Super-Resolution with Multi-Gram Loss release_thbnxnljgbc25ktechw5w2yiam

by Yong Shi, Biao Li, Bo Wang, Zhiquan Qi, Jiabin Liu

Published in Electronics by MDPI AG.

2019   p833

Abstract

Recently, supervised deep super-resolution (SR) networks have achieved great success in both accuracy and texture generation. However, most methods train in the dataset with a fixed kernel (such as bicubic) between high-resolution images and their low-resolution counterparts. In real-life applications, pictures are always disturbed with additional artifacts, e.g., non-ideal point-spread function in old film photos, and compression loss in cellphone photos. How to generate a satisfactory SR image from the specific prior single low-resolution (LR) image is still a challenging issue. In this paper, we propose a novel unsupervised method named unsupervised single-image SR with multi-gram loss (UMGSR) to overcome the dilemma. There are two significant contributions in this paper: (a) we design a new architecture for extracting more information from limited inputs by combining the local residual block and two-step global residual learning; (b) we introduce the multi-gram loss for SR task to effectively generate better image details. Experimental comparison shows that our unsupervised method in normal conditions can attain better visual results than other supervised SR methods.
In application/xml+jats format

Archived Files and Locations

application/pdf  2.3 MB
file_en4hncghyjbtxacoz5e3orvwme
web.archive.org (webarchive)
res.mdpi.com (publisher)
Read Archived PDF
Preserved and Accessible
Type  article-journal
Stage   published
Date   2019-07-26
Language   en ?
Container Metadata
Open Access Publication
In DOAJ
In ISSN ROAD
In Keepers Registry
ISSN-L:  2079-9292
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: d07cba12-209b-4134-a0c0-a49ef85a3cf2
API URL: JSON