NTIRE 2017 Challenge on Single Image Super-Resolution: Methods and Results

Radu Timofte, Eirikur Agustsson, Luc Van Gool, Ming Hsuan Yang, Lei Zhang, Bee Lim, Sanghyun Son, Heewon Kim, Seungjun Nah, Kyoung Mu Lee, Xintao Wang, Yapeng Tian, Ke Yu, Yulun Zhang, Shixiang Wu, Chao Dong, Liang Lin, Yu Qiao, Chen Change Loy, Woong BaeJaejun Yoo, Yoseob Han, Jong Chul Ye, Jae Seok Choi, Munchurl Kim, Yuchen Fan, Jiahui Yu, Wei Han, Ding Liu, Haichao Yu, Zhangyang Wang, Honghui Shi, Xinchao Wang, Thomas S. Huang, Yunjin Chen, Kai Zhang, Wangmeng Zuo, Zhimin Tang, Linkai Luo, Shaohui Li, Min Fu, Lei Cao, Wen Heng, Giang Bui, Truc Le, Ye Duan, Dacheng Tao, Ruxin Wang, Xu Lin, Jianxin Pang, Jinchang Xu, Yu Zhao, Xiangyu Xu, Jinshan Pan, Deqing Sun, Yujin Zhang, Xibin Song, Yuchao Dai, Xueying Qin, Xuan Phung Huynh, Tiantong Guo, Hojjat Seyed Mousavi, Tiep Huu Vu, Vishal Monga, Cristovao Cruz, Karen Egiazarian, Vladimir Katkovnik, Rakesh Mehta, Arnav Kumar Jain, Abhinav Agarwalla, Ch V.Sai Praveen, Ruofan Zhou, Hongdiao Wen, Che Zhu, Zhiqiang Xia, Zhengtao Wang, Qi Guo

Research output: Chapter in Book/Report/Conference proceedingConference contribution

157 Citations (Scopus)

Abstract

This paper reviews the first challenge on single image super-resolution (restoration of rich details in an low resolution image) with focus on proposed solutions and results. A new DIVerse 2K resolution image dataset (DIV2K) was employed. The challenge had 6 competitions divided into 2 tracks with 3 magnification factors each. Track 1 employed the standard bicubic downscaling setup, while Track 2 had unknown downscaling operators (blur kernel and decimation) but learnable through low and high res train images. Each competition had b∼100 registered participants and 20 teams competed in the final testing phase. They gauge the state-of-the-art in single image super-resolution.

Original languageEnglish
Title of host publicationProceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017
PublisherIEEE Computer Society
Pages1110-1121
Number of pages12
ISBN (Electronic)9781538607336
DOIs
Publication statusPublished - 2017 Aug 22
Event30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017 - Honolulu, United States
Duration: 2017 Jul 212017 Jul 26

Publication series

NameIEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Volume2017-July
ISSN (Print)2160-7508
ISSN (Electronic)2160-7516

Conference

Conference30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017
CountryUnited States
CityHonolulu
Period17/7/2117/7/26

Fingerprint

Image resolution
Optical resolving power
Restoration
Gages
Testing

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

Timofte, R., Agustsson, E., Gool, L. V., Yang, M. H., Zhang, L., Lim, B., ... Guo, Q. (2017). NTIRE 2017 Challenge on Single Image Super-Resolution: Methods and Results. In Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017 (pp. 1110-1121). [8014883] (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2017-July). IEEE Computer Society. https://doi.org/10.1109/CVPRW.2017.149
Timofte, Radu ; Agustsson, Eirikur ; Gool, Luc Van ; Yang, Ming Hsuan ; Zhang, Lei ; Lim, Bee ; Son, Sanghyun ; Kim, Heewon ; Nah, Seungjun ; Lee, Kyoung Mu ; Wang, Xintao ; Tian, Yapeng ; Yu, Ke ; Zhang, Yulun ; Wu, Shixiang ; Dong, Chao ; Lin, Liang ; Qiao, Yu ; Loy, Chen Change ; Bae, Woong ; Yoo, Jaejun ; Han, Yoseob ; Ye, Jong Chul ; Choi, Jae Seok ; Kim, Munchurl ; Fan, Yuchen ; Yu, Jiahui ; Han, Wei ; Liu, Ding ; Yu, Haichao ; Wang, Zhangyang ; Shi, Honghui ; Wang, Xinchao ; Huang, Thomas S. ; Chen, Yunjin ; Zhang, Kai ; Zuo, Wangmeng ; Tang, Zhimin ; Luo, Linkai ; Li, Shaohui ; Fu, Min ; Cao, Lei ; Heng, Wen ; Bui, Giang ; Le, Truc ; Duan, Ye ; Tao, Dacheng ; Wang, Ruxin ; Lin, Xu ; Pang, Jianxin ; Xu, Jinchang ; Zhao, Yu ; Xu, Xiangyu ; Pan, Jinshan ; Sun, Deqing ; Zhang, Yujin ; Song, Xibin ; Dai, Yuchao ; Qin, Xueying ; Huynh, Xuan Phung ; Guo, Tiantong ; Mousavi, Hojjat Seyed ; Vu, Tiep Huu ; Monga, Vishal ; Cruz, Cristovao ; Egiazarian, Karen ; Katkovnik, Vladimir ; Mehta, Rakesh ; Jain, Arnav Kumar ; Agarwalla, Abhinav ; Praveen, Ch V.Sai ; Zhou, Ruofan ; Wen, Hongdiao ; Zhu, Che ; Xia, Zhiqiang ; Wang, Zhengtao ; Guo, Qi. / NTIRE 2017 Challenge on Single Image Super-Resolution : Methods and Results. Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017. IEEE Computer Society, 2017. pp. 1110-1121 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops).
@inproceedings{0028c6e0696b4d74b375fa074f4a576c,
title = "NTIRE 2017 Challenge on Single Image Super-Resolution: Methods and Results",
abstract = "This paper reviews the first challenge on single image super-resolution (restoration of rich details in an low resolution image) with focus on proposed solutions and results. A new DIVerse 2K resolution image dataset (DIV2K) was employed. The challenge had 6 competitions divided into 2 tracks with 3 magnification factors each. Track 1 employed the standard bicubic downscaling setup, while Track 2 had unknown downscaling operators (blur kernel and decimation) but learnable through low and high res train images. Each competition had b∼100 registered participants and 20 teams competed in the final testing phase. They gauge the state-of-the-art in single image super-resolution.",
author = "Radu Timofte and Eirikur Agustsson and Gool, {Luc Van} and Yang, {Ming Hsuan} and Lei Zhang and Bee Lim and Sanghyun Son and Heewon Kim and Seungjun Nah and Lee, {Kyoung Mu} and Xintao Wang and Yapeng Tian and Ke Yu and Yulun Zhang and Shixiang Wu and Chao Dong and Liang Lin and Yu Qiao and Loy, {Chen Change} and Woong Bae and Jaejun Yoo and Yoseob Han and Ye, {Jong Chul} and Choi, {Jae Seok} and Munchurl Kim and Yuchen Fan and Jiahui Yu and Wei Han and Ding Liu and Haichao Yu and Zhangyang Wang and Honghui Shi and Xinchao Wang and Huang, {Thomas S.} and Yunjin Chen and Kai Zhang and Wangmeng Zuo and Zhimin Tang and Linkai Luo and Shaohui Li and Min Fu and Lei Cao and Wen Heng and Giang Bui and Truc Le and Ye Duan and Dacheng Tao and Ruxin Wang and Xu Lin and Jianxin Pang and Jinchang Xu and Yu Zhao and Xiangyu Xu and Jinshan Pan and Deqing Sun and Yujin Zhang and Xibin Song and Yuchao Dai and Xueying Qin and Huynh, {Xuan Phung} and Tiantong Guo and Mousavi, {Hojjat Seyed} and Vu, {Tiep Huu} and Vishal Monga and Cristovao Cruz and Karen Egiazarian and Vladimir Katkovnik and Rakesh Mehta and Jain, {Arnav Kumar} and Abhinav Agarwalla and Praveen, {Ch V.Sai} and Ruofan Zhou and Hongdiao Wen and Che Zhu and Zhiqiang Xia and Zhengtao Wang and Qi Guo",
year = "2017",
month = "8",
day = "22",
doi = "10.1109/CVPRW.2017.149",
language = "English",
series = "IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops",
publisher = "IEEE Computer Society",
pages = "1110--1121",
booktitle = "Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017",
address = "United States",

}

Timofte, R, Agustsson, E, Gool, LV, Yang, MH, Zhang, L, Lim, B, Son, S, Kim, H, Nah, S, Lee, KM, Wang, X, Tian, Y, Yu, K, Zhang, Y, Wu, S, Dong, C, Lin, L, Qiao, Y, Loy, CC, Bae, W, Yoo, J, Han, Y, Ye, JC, Choi, JS, Kim, M, Fan, Y, Yu, J, Han, W, Liu, D, Yu, H, Wang, Z, Shi, H, Wang, X, Huang, TS, Chen, Y, Zhang, K, Zuo, W, Tang, Z, Luo, L, Li, S, Fu, M, Cao, L, Heng, W, Bui, G, Le, T, Duan, Y, Tao, D, Wang, R, Lin, X, Pang, J, Xu, J, Zhao, Y, Xu, X, Pan, J, Sun, D, Zhang, Y, Song, X, Dai, Y, Qin, X, Huynh, XP, Guo, T, Mousavi, HS, Vu, TH, Monga, V, Cruz, C, Egiazarian, K, Katkovnik, V, Mehta, R, Jain, AK, Agarwalla, A, Praveen, CVS, Zhou, R, Wen, H, Zhu, C, Xia, Z, Wang, Z & Guo, Q 2017, NTIRE 2017 Challenge on Single Image Super-Resolution: Methods and Results. in Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017., 8014883, IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, vol. 2017-July, IEEE Computer Society, pp. 1110-1121, 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017, Honolulu, United States, 17/7/21. https://doi.org/10.1109/CVPRW.2017.149

NTIRE 2017 Challenge on Single Image Super-Resolution : Methods and Results. / Timofte, Radu; Agustsson, Eirikur; Gool, Luc Van; Yang, Ming Hsuan; Zhang, Lei; Lim, Bee; Son, Sanghyun; Kim, Heewon; Nah, Seungjun; Lee, Kyoung Mu; Wang, Xintao; Tian, Yapeng; Yu, Ke; Zhang, Yulun; Wu, Shixiang; Dong, Chao; Lin, Liang; Qiao, Yu; Loy, Chen Change; Bae, Woong; Yoo, Jaejun; Han, Yoseob; Ye, Jong Chul; Choi, Jae Seok; Kim, Munchurl; Fan, Yuchen; Yu, Jiahui; Han, Wei; Liu, Ding; Yu, Haichao; Wang, Zhangyang; Shi, Honghui; Wang, Xinchao; Huang, Thomas S.; Chen, Yunjin; Zhang, Kai; Zuo, Wangmeng; Tang, Zhimin; Luo, Linkai; Li, Shaohui; Fu, Min; Cao, Lei; Heng, Wen; Bui, Giang; Le, Truc; Duan, Ye; Tao, Dacheng; Wang, Ruxin; Lin, Xu; Pang, Jianxin; Xu, Jinchang; Zhao, Yu; Xu, Xiangyu; Pan, Jinshan; Sun, Deqing; Zhang, Yujin; Song, Xibin; Dai, Yuchao; Qin, Xueying; Huynh, Xuan Phung; Guo, Tiantong; Mousavi, Hojjat Seyed; Vu, Tiep Huu; Monga, Vishal; Cruz, Cristovao; Egiazarian, Karen; Katkovnik, Vladimir; Mehta, Rakesh; Jain, Arnav Kumar; Agarwalla, Abhinav; Praveen, Ch V.Sai; Zhou, Ruofan; Wen, Hongdiao; Zhu, Che; Xia, Zhiqiang; Wang, Zhengtao; Guo, Qi.

Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017. IEEE Computer Society, 2017. p. 1110-1121 8014883 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2017-July).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - NTIRE 2017 Challenge on Single Image Super-Resolution

T2 - Methods and Results

AU - Timofte, Radu

AU - Agustsson, Eirikur

AU - Gool, Luc Van

AU - Yang, Ming Hsuan

AU - Zhang, Lei

AU - Lim, Bee

AU - Son, Sanghyun

AU - Kim, Heewon

AU - Nah, Seungjun

AU - Lee, Kyoung Mu

AU - Wang, Xintao

AU - Tian, Yapeng

AU - Yu, Ke

AU - Zhang, Yulun

AU - Wu, Shixiang

AU - Dong, Chao

AU - Lin, Liang

AU - Qiao, Yu

AU - Loy, Chen Change

AU - Bae, Woong

AU - Yoo, Jaejun

AU - Han, Yoseob

AU - Ye, Jong Chul

AU - Choi, Jae Seok

AU - Kim, Munchurl

AU - Fan, Yuchen

AU - Yu, Jiahui

AU - Han, Wei

AU - Liu, Ding

AU - Yu, Haichao

AU - Wang, Zhangyang

AU - Shi, Honghui

AU - Wang, Xinchao

AU - Huang, Thomas S.

AU - Chen, Yunjin

AU - Zhang, Kai

AU - Zuo, Wangmeng

AU - Tang, Zhimin

AU - Luo, Linkai

AU - Li, Shaohui

AU - Fu, Min

AU - Cao, Lei

AU - Heng, Wen

AU - Bui, Giang

AU - Le, Truc

AU - Duan, Ye

AU - Tao, Dacheng

AU - Wang, Ruxin

AU - Lin, Xu

AU - Pang, Jianxin

AU - Xu, Jinchang

AU - Zhao, Yu

AU - Xu, Xiangyu

AU - Pan, Jinshan

AU - Sun, Deqing

AU - Zhang, Yujin

AU - Song, Xibin

AU - Dai, Yuchao

AU - Qin, Xueying

AU - Huynh, Xuan Phung

AU - Guo, Tiantong

AU - Mousavi, Hojjat Seyed

AU - Vu, Tiep Huu

AU - Monga, Vishal

AU - Cruz, Cristovao

AU - Egiazarian, Karen

AU - Katkovnik, Vladimir

AU - Mehta, Rakesh

AU - Jain, Arnav Kumar

AU - Agarwalla, Abhinav

AU - Praveen, Ch V.Sai

AU - Zhou, Ruofan

AU - Wen, Hongdiao

AU - Zhu, Che

AU - Xia, Zhiqiang

AU - Wang, Zhengtao

AU - Guo, Qi

PY - 2017/8/22

Y1 - 2017/8/22

N2 - This paper reviews the first challenge on single image super-resolution (restoration of rich details in an low resolution image) with focus on proposed solutions and results. A new DIVerse 2K resolution image dataset (DIV2K) was employed. The challenge had 6 competitions divided into 2 tracks with 3 magnification factors each. Track 1 employed the standard bicubic downscaling setup, while Track 2 had unknown downscaling operators (blur kernel and decimation) but learnable through low and high res train images. Each competition had b∼100 registered participants and 20 teams competed in the final testing phase. They gauge the state-of-the-art in single image super-resolution.

AB - This paper reviews the first challenge on single image super-resolution (restoration of rich details in an low resolution image) with focus on proposed solutions and results. A new DIVerse 2K resolution image dataset (DIV2K) was employed. The challenge had 6 competitions divided into 2 tracks with 3 magnification factors each. Track 1 employed the standard bicubic downscaling setup, while Track 2 had unknown downscaling operators (blur kernel and decimation) but learnable through low and high res train images. Each competition had b∼100 registered participants and 20 teams competed in the final testing phase. They gauge the state-of-the-art in single image super-resolution.

UR - http://www.scopus.com/inward/record.url?scp=85030220122&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85030220122&partnerID=8YFLogxK

U2 - 10.1109/CVPRW.2017.149

DO - 10.1109/CVPRW.2017.149

M3 - Conference contribution

AN - SCOPUS:85030220122

T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

SP - 1110

EP - 1121

BT - Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017

PB - IEEE Computer Society

ER -

Timofte R, Agustsson E, Gool LV, Yang MH, Zhang L, Lim B et al. NTIRE 2017 Challenge on Single Image Super-Resolution: Methods and Results. In Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017. IEEE Computer Society. 2017. p. 1110-1121. 8014883. (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). https://doi.org/10.1109/CVPRW.2017.149