Ajou University repository

Deep image prior for super resolution of noisy imageoa mark
Citations

SCOPUS

7

Citation Export

Publication Year
2021-08-02
Journal
Electronics (Switzerland)
Publisher
MDPI AG
Citation
Electronics (Switzerland), Vol.10 No.16
Keyword
Deep image priorImage restorationSuper-resolution
All Science Classification Codes (ASJC)
Control and Systems EngineeringSignal ProcessingHardware and ArchitectureComputer Networks and CommunicationsElectrical and Electronic Engineering
Abstract
Single image super-resolution task aims to reconstruct a high-resolution image from a low-resolution image. Recently, it has been shown that by using deep image prior (DIP), a single neural network is sufficient to capture low-level image statistics using only a single image without data-driven training such that it can be used for various image restoration problems. However, super-resolution tasks are difficult to perform with DIP when the target image is noisy. The super-resolved image becomes noisy because the reconstruction loss of DIP does not consider the noise in the target image. Furthermore, when the target image contains noise, the optimization process of DIP becomes unstable and sensitive to noise. In this paper, we propose a noise-robust and stable framework based on DIP. To this end, we propose a noise-estimation method using the generative adversarial network (GAN) and self-supervision loss (SSL). We show that a generator of DIP can learn the distribution of noise in the target image with the proposed framework. Moreover, we argue that the optimization process of DIP is stabilized when the proposed self-supervision loss is incorporated. The experiments show that the proposed method quantitatively and qualitatively outperforms existing single image super-resolution methods for noisy images.
ISSN
2079-9292
Language
eng
URI
https://aurora.ajou.ac.kr/handle/2018.oak/32226
https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85113733800&origin=inward
DOI
https://doi.org/10.3390/electronics10162014
Journal URL
https://www.mdpi.com/2079-9292/10/16/2014/pdf
Type
Article
Funding
Funding: This work was supported by the Ministry of Science and ICT (MSIT), South Korea, under the Information Technology Research Center (ITRC) Support Program supervised by the Institute for Information and Communications Technology Promotion (IITP) under Grant IITP-2021-2018-0-01424.
Show full item record

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Heo,Yong Seok  Image
Heo,Yong Seok 허용석
Department of Electrical and Computer Engineering
Read More

Total Views & Downloads

File Download