[논문]Single Image Super-Resolution via Similarity Between Spatially Scattered Features

Ha, Jeonghyo; Kim, Youngsoo; Kim, Junmo

doi:10.1109/access.2020.3011566

[해외논문] Single Image Super-Resolution via Similarity Between Spatially Scattered Features 원문보기

IEEE access : practical research, open solutions, v.8, 2020년, pp.137672 - 137682

Ha, Jeonghyo (Division of Future Vehicle, Korea Advanced Institute of Science and Technology, Daejeon, South Korea) , Kim, Youngsoo (School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea) , Kim, Junmo (Division of Future Vehicle, Korea Advanced Institute of Science and Technology, Daejeon, South Korea)

Abstract ▼ AI-Helper

The development of convolutional neural networks (CNN) has remarkably improved the current research on single image super-resolution (SISR). Several high-quality studies have been performed on reconstruction accuracy and perceptual quality, which are the two main issues in SISR. Nevertheless, numerous problems in SISR remain unsolved. SISR is inherently an ill-posed problem owing to insufficient information, and as the scale factor increases, the lack of information becomes even more pronounced. We have studied ways to solve the local characteristics of CNN to deal with additional useful information. A CNN uses a convolution layer designed based on local features, and repeatedly accumulates these features to expand a receptive field. We have explored network structures that can directly handle global information even at lower layers, which are not covered by the receptive field of a CNN. In this paper, we propose a non-local attention SISR network (NASR) that generates and utilizes the globally scattered similarity information of features. In addition, we propose a very deep architecture based on dense blocks that does not suffer from gradient vanishing without any normalization. Experimental results on standard benchmark datasets indicate the effectiveness of the proposed network, which exhibits state-of-the-art performance in terms of reconstruction accuracy and perceptual quality.

참고문헌 (46)

Proc IEEE Intl Conf on Learn Repr (ICLR) Residual non-local attention networks for image restoration zhang 2019 1
Proc European Conf Comp Vis Workshop Analyzing perception-distortion tradeoff using enhanced perceptual super-resolution network vasu 2018 114
Proc Eur Conf Comput Vis (ECCV) Perceptual losses for real-time style transfer and super-resolution johnson 2016 694
Proc Eur Conf Comput Vis (ECCV) CBAM: Convolutional block attention module woo 2018 3
Proc Eur Conf Comput Vis (ECCV) Fast, accurate, and lightweight super-resolution with cascading residual network ahn 2018 256
Proc Eur Conf Comput Vis (ECCV) Image super-resolution using very deep residual channel attention networks zhang 2018 294
Proc European Conf Comp Vis Workshop Multi-scale recursive and perception-distortion controllable image super-resolution michelini 2018 3
Proc European Conf Comp Vis Workshop The 2018 PIRM challenge on perceptual image super-resolution blau 2018 334
10.1109/ICASSP40776.2020.9054071
Proc Eur Conf Comput Vis (ECCV) Learning a deep convolutional network for image super-resolution dong 2014 184
10.1109/CVPRW.2017.150
Hu, Yanting, Li, Jie, Huang, Yuanfei, Gao, Xinbo. Channel-Wise and Spatial Feature Modulation Network for Single Image Super-Resolution. IEEE transactions on circuits and systems for video technology : a publication of the Circuits and Systems Society, vol.30, no.11, 3911-3927.

상세보기
Proc IEEE Conf Comput Vis Pattern Recognit Workshops (CVPRW) NTIRE 2017 challenge on single image super–resolution: Methods and results agustsson 2017 1110
10.1109/CVPR.2018.00813
10.1109/CVPR.2018.00179
10.1109/CVPR.2018.00745
10.1109/CVPR.2018.00070
10.1109/CVPR.2018.00262
10.1109/CVPR.2018.00178
10.1109/CVPR.2019.01132
10.1109/CVPR.2019.00183
10.1109/ICCV.2001.937655
10.1109/CVPR.2016.181
10.1109/ICCV.2017.514
10.1109/CVPR.2016.182
10.1109/CVPR.2017.298
10.1109/ICCV.2019.00280
10.1109/CVPRW.2017.151
10.1109/CVPR.2017.243
10.1109/CVPR.2017.618
10.1109/CVPR.2016.90
10.1109/CVPR.2017.19
10.1109/CVPR.2015.7299156
arXiv 1811 12043 MAMNet: Multi-path adaptive modulation network for image super-resolution kim 2018
10.1109/CVPR.2005.38
arXiv 1806 01261 Relational inductive biases, deep learning, and graph networks battaglia 2018
Proc Adv Neural Inf Process Syst Generative adversarial nets goodfellow 2014 2672
Proc Adv Neural Inf Process Syst (NIPS) Imagenet classifcation with deep convolutional neural networks krizhevsky 2012 1097
Proc Int Conf Curves Surf On single image scale-up using sparse-representations zeyde 2012 10.1007/978-3-642-27413-8_47 711

상세보기
Proc Adv Neural Inf Process Syst (NIPS) Non-local recurrent network for image restoration liu 2018 1673
10.5244/C.26.135
Proc Adv Neural Inf Process Syst (NIPS) Attention is all you need vaswani 2017 5998
arXiv 1904 02358 Lightweight image super-resolution with adaptive weighted learning network wang 2019
10.1109/ICCV.2017.481
Matsui, Yusuke, Ito, Kota, Aramaki, Yuji, Fujimoto, Azuma, Ogawa, Toru, Yamasaki, Toshihiko, Aizawa, Kiyoharu. Sketch-based manga retrieval using manga109 dataset. Multimedia tools and applications, vol.76, no.20, 21811-21838.

상세보기
Proc Adv Neural Inf Process Syst (NIPS) Neural nearest neighbors networks plãötz 2018 1087

LOADING...

활용도 분석정보

상세보기

다운로드

내보내기

활용도 Top5 논문

해당 논문의 주제분야에서 활용도가 높은 상위 5개 콘텐츠를 보여줍니다.
더보기 버튼을 클릭하시면 더 많은 관련자료를 살펴볼 수 있습니다.

원문 보기

AccessON 원문보기

원문 URL 링크

DOI : 10.1109/ACCESS.2020.3011566 [무료]
IEEE : 저널 > 논문 [무료]
AccessON : 저널

*원문 PDF 파일 및 링크정보가 존재하지 않을 경우 KISTI DDS 시스템에서 제공하는 원문복사서비스를 사용할 수 있습니다.

오픈액세스(OA) 유형

GOLD

오픈액세스 학술지에 출판된 논문

저작권 관리 안내

내보내기 메뉴

내보내기 구분

파일저장
인쇄
메일전송

구성항목

기본정보
상세정보

관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관

저장형식

Text(ASCII format)
Excel format
RefWorks Direct Export
RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley

메일정보

받는사람 (필수): @
보내는사람 (선택): @
제목
내용: KISTI 검색결과 이메일 서비스

안내

총 건의 자료가 검색되었습니다.

다운받으실 자료의 인덱스를 입력하세요. (1-10,000)

검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다.

데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요)

다운로드 파일은 UTF-8 형태로 저장됩니다.
파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오.

Text(ASCII format)
Excel format

표제어: PCR

동의어: Packet Collision Rate

용어 설명 출처 목록 (6)

용어 설명: PCR은 세균 특이성이 있는 primer를 이용하여 적은 수의 세균이 있을지라도 쉽게 검출할 수 있는 유용한 방법이며, 이를 이용하여 구강 내 치면세균막이나 타액에서 직접 세균을 검출할 수 있게 되었다[8].

AI-Helper ※ AI-Helper는 을 사용합니다.

AI-Helper

안녕하세요, AI-Helper입니다. 좌측 "선택된 텍스트"에서 텍스트를 선택하여 요약, 번역, 용어설명을 실행하세요.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.

연합인증