NTIRE 2020 challenge on perceptual extreme super-resolution: Methods and results

Kai Zhang; Shuhang Gu; Radu Timofte; Taizhang Shang; Qiuju Dai; Shengchen Zhu; Tong Yang; Yandong Guo; Younghyun Jo; Sejong Yang; Seon Joo Kim; Lin Zha; Jiande Jiang; Xinbo Gao; Wen Lu; Jing Liu; Kwangjin Yoon; Taegyun Jeon; Kazutoshi Akita; Takeru Ooba; Norimichi Ukita; Zhipeng Luo; Yuehan Yao; Zhenyu Xu; Dongliang He; Wenhao Wu; Yukang Ding; Chao Li; Fu Li; Shilei Wen; Jianwei Li; Fuzhi Yang; Huan Yang; Jianlong Fu; Byung Hoon Kim; Jaehyun Baek; Jong Chul Ye; Yuchen Fan; Thomas S. Huang; Junyeop Lee; Bokyeung Lee; Jungki Min; Gwantae Kim; Kanghyu Lee; Jaihyun Park; Mykola Mykhailych; Haoyu Zhong; Yukai Shi; Xiaojun Yang; Zhijing Yang; Liang Lin; Tongtong Zhao; Jinjia Peng; Huibing Wang; Zhi Jin; Jiahao Wu; Yifu Chen; Chenming Shang; Huanrong Zhang; Jeongki Min; Hrishikesh Ps; Densen Puthussery; Jiji Cv

doi:10.1109/CVPRW50498.2020.00254

NTIRE 2020 challenge on perceptual extreme super-resolution: Methods and results

Kai Zhang, Shuhang Gu, Radu Timofte, Taizhang Shang, Qiuju Dai, Shengchen Zhu, Tong Yang, Yandong Guo, Younghyun Jo, Sejong Yang, Seon Joo Kim, Lin Zha, Jiande Jiang, Xinbo Gao, Wen Lu, Jing Liu, Kwangjin Yoon, Taegyun Jeon, Kazutoshi Akita, Takeru OobaNorimichi Ukita, Zhipeng Luo, Yuehan Yao, Zhenyu Xu, Dongliang He, Wenhao Wu, Yukang Ding, Chao Li, Fu Li, Shilei Wen, Jianwei Li, Fuzhi Yang, Huan Yang, Jianlong Fu, Byung Hoon Kim, Jaehyun Baek, Jong Chul Ye, Yuchen Fan, Thomas S. Huang, Junyeop Lee, Bokyeung Lee, Jungki Min, Gwantae Kim, Kanghyu Lee, Jaihyun Park, Mykola Mykhailych, Haoyu Zhong, Yukai Shi, Xiaojun Yang, Zhijing Yang, Liang Lin, Tongtong Zhao, Jinjia Peng, Huibing Wang, Zhi Jin, Jiahao Wu, Yifu Chen, Chenming Shang, Huanrong Zhang, Jeongki Min, Hrishikesh Ps, Densen Puthussery, Jiji Cv

College of Computing

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

32 Citations (Scopus)

Abstract

This paper reviews the NTIRE 2020 challenge on perceptual extreme super-resolution with focus on proposed solutions and results. The challenge task was to super-resolve an input image with a magnification factor ×16 based on a set of prior examples of low and corresponding high resolution images. The goal is to obtain a network design capable to produce high resolution results with the best perceptual quality and similar to the ground truth. The track had 280 registered participants, and19 teams submitted the final results. They gauge the state-of-the-art in single image super-resolution.

Original language	English
Title of host publication	Proceedings - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020
Publisher	IEEE Computer Society
Pages	2045-2057
Number of pages	13
ISBN (Electronic)	9781728193601
DOIs	https://doi.org/10.1109/CVPRW50498.2020.00254
Publication status	Published - 2020 Jun
Event	2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020 - Virtual, Online, United States Duration: 2020 Jun 14 → 2020 Jun 19

Publication series

Name	IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Volume	2020-June
ISSN (Print)	2160-7508
ISSN (Electronic)	2160-7516

Conference

Conference	2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020
Country/Territory	United States
City	Virtual, Online
Period	20/6/14 → 20/6/19

Bibliographical note

Publisher Copyright:
© 2020 IEEE.

All Science Journal Classification (ASJC) codes

Computer Vision and Pattern Recognition
Electrical and Electronic Engineering

Access to Document

10.1109/CVPRW50498.2020.00254

Cite this

Zhang, K., Gu, S., Timofte, R., Shang, T., Dai, Q., Zhu, S., Yang, T., Guo, Y., Jo, Y., Yang, S., Kim, S. J., Zha, L., Jiang, J., Gao, X., Lu, W., Liu, J., Yoon, K., Jeon, T., Akita, K., ... Cv, J. (2020). NTIRE 2020 challenge on perceptual extreme super-resolution: Methods and results. In Proceedings - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020 (pp. 2045-2057). [9150605] (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2020-June). IEEE Computer Society. https://doi.org/10.1109/CVPRW50498.2020.00254

@inproceedings{87d85bb1189d4341853fea6973114405,

title = "NTIRE 2020 challenge on perceptual extreme super-resolution: Methods and results",

abstract = "This paper reviews the NTIRE 2020 challenge on perceptual extreme super-resolution with focus on proposed solutions and results. The challenge task was to super-resolve an input image with a magnification factor ×16 based on a set of prior examples of low and corresponding high resolution images. The goal is to obtain a network design capable to produce high resolution results with the best perceptual quality and similar to the ground truth. The track had 280 registered participants, and19 teams submitted the final results. They gauge the state-of-the-art in single image super-resolution.",

author = "Kai Zhang and Shuhang Gu and Radu Timofte and Taizhang Shang and Qiuju Dai and Shengchen Zhu and Tong Yang and Yandong Guo and Younghyun Jo and Sejong Yang and Kim, {Seon Joo} and Lin Zha and Jiande Jiang and Xinbo Gao and Wen Lu and Jing Liu and Kwangjin Yoon and Taegyun Jeon and Kazutoshi Akita and Takeru Ooba and Norimichi Ukita and Zhipeng Luo and Yuehan Yao and Zhenyu Xu and Dongliang He and Wenhao Wu and Yukang Ding and Chao Li and Fu Li and Shilei Wen and Jianwei Li and Fuzhi Yang and Huan Yang and Jianlong Fu and Kim, {Byung Hoon} and Jaehyun Baek and Ye, {Jong Chul} and Yuchen Fan and Huang, {Thomas S.} and Junyeop Lee and Bokyeung Lee and Jungki Min and Gwantae Kim and Kanghyu Lee and Jaihyun Park and Mykola Mykhailych and Haoyu Zhong and Yukai Shi and Xiaojun Yang and Zhijing Yang and Liang Lin and Tongtong Zhao and Jinjia Peng and Huibing Wang and Zhi Jin and Jiahao Wu and Yifu Chen and Chenming Shang and Huanrong Zhang and Jeongki Min and Hrishikesh Ps and Densen Puthussery and Jiji Cv",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020 ; Conference date: 14-06-2020 Through 19-06-2020",

year = "2020",

month = jun,

doi = "10.1109/CVPRW50498.2020.00254",

language = "English",

series = "IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops",

publisher = "IEEE Computer Society",

pages = "2045--2057",

booktitle = "Proceedings - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020",

address = "United States",

}

Zhang, K, Gu, S, Timofte, R, Shang, T, Dai, Q, Zhu, S, Yang, T, Guo, Y, Jo, Y, Yang, S, Kim, SJ, Zha, L, Jiang, J, Gao, X, Lu, W, Liu, J, Yoon, K, Jeon, T, Akita, K, Ooba, T, Ukita, N, Luo, Z, Yao, Y, Xu, Z, He, D, Wu, W, Ding, Y, Li, C, Li, F, Wen, S, Li, J, Yang, F, Yang, H, Fu, J, Kim, BH, Baek, J, Ye, JC, Fan, Y, Huang, TS, Lee, J, Lee, B, Min, J, Kim, G, Lee, K, Park, J, Mykhailych, M, Zhong, H, Shi, Y, Yang, X, Yang, Z, Lin, L, Zhao, T, Peng, J, Wang, H, Jin, Z, Wu, J, Chen, Y, Shang, C, Zhang, H, Min, J, Ps, H, Puthussery, D & Cv, J 2020, NTIRE 2020 challenge on perceptual extreme super-resolution: Methods and results. in Proceedings - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020., 9150605, IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, vol. 2020-June, IEEE Computer Society, pp. 2045-2057, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020, Virtual, Online, United States, 20/6/14. https://doi.org/10.1109/CVPRW50498.2020.00254

NTIRE 2020 challenge on perceptual extreme super-resolution : Methods and results. / Zhang, Kai; Gu, Shuhang; Timofte, Radu et al.

Proceedings - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020. IEEE Computer Society, 2020. p. 2045-2057 9150605 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2020-June).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - NTIRE 2020 challenge on perceptual extreme super-resolution

T2 - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020

AU - Zhang, Kai

AU - Gu, Shuhang

AU - Timofte, Radu

AU - Shang, Taizhang

AU - Dai, Qiuju

AU - Zhu, Shengchen

AU - Yang, Tong

AU - Guo, Yandong

AU - Jo, Younghyun

AU - Yang, Sejong

AU - Kim, Seon Joo

AU - Zha, Lin

AU - Jiang, Jiande

AU - Gao, Xinbo

AU - Lu, Wen

AU - Liu, Jing

AU - Yoon, Kwangjin

AU - Jeon, Taegyun

AU - Akita, Kazutoshi

AU - Ooba, Takeru

AU - Ukita, Norimichi

AU - Luo, Zhipeng

AU - Yao, Yuehan

AU - Xu, Zhenyu

AU - He, Dongliang

AU - Wu, Wenhao

AU - Ding, Yukang

AU - Li, Chao

AU - Li, Fu

AU - Wen, Shilei

AU - Li, Jianwei

AU - Yang, Fuzhi

AU - Yang, Huan

AU - Fu, Jianlong

AU - Kim, Byung Hoon

AU - Baek, Jaehyun

AU - Ye, Jong Chul

AU - Fan, Yuchen

AU - Huang, Thomas S.

AU - Lee, Junyeop

AU - Lee, Bokyeung

AU - Min, Jungki

AU - Kim, Gwantae

AU - Lee, Kanghyu

AU - Park, Jaihyun

AU - Mykhailych, Mykola

AU - Zhong, Haoyu

AU - Shi, Yukai

AU - Yang, Xiaojun

AU - Yang, Zhijing

AU - Lin, Liang

AU - Zhao, Tongtong

AU - Peng, Jinjia

AU - Wang, Huibing

AU - Jin, Zhi

AU - Wu, Jiahao

AU - Chen, Yifu

AU - Shang, Chenming

AU - Zhang, Huanrong

AU - Min, Jeongki

AU - Ps, Hrishikesh

AU - Puthussery, Densen

AU - Cv, Jiji

PY - 2020/6

Y1 - 2020/6

N2 - This paper reviews the NTIRE 2020 challenge on perceptual extreme super-resolution with focus on proposed solutions and results. The challenge task was to super-resolve an input image with a magnification factor ×16 based on a set of prior examples of low and corresponding high resolution images. The goal is to obtain a network design capable to produce high resolution results with the best perceptual quality and similar to the ground truth. The track had 280 registered participants, and19 teams submitted the final results. They gauge the state-of-the-art in single image super-resolution.

AB - This paper reviews the NTIRE 2020 challenge on perceptual extreme super-resolution with focus on proposed solutions and results. The challenge task was to super-resolve an input image with a magnification factor ×16 based on a set of prior examples of low and corresponding high resolution images. The goal is to obtain a network design capable to produce high resolution results with the best perceptual quality and similar to the ground truth. The track had 280 registered participants, and19 teams submitted the final results. They gauge the state-of-the-art in single image super-resolution.

UR - http://www.scopus.com/inward/record.url?scp=85090137648&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85090137648&partnerID=8YFLogxK

U2 - 10.1109/CVPRW50498.2020.00254

DO - 10.1109/CVPRW50498.2020.00254

M3 - Conference contribution

AN - SCOPUS:85090137648

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

SP - 2045

EP - 2057

BT - Proceedings - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020

PB - IEEE Computer Society

Y2 - 14 June 2020 through 19 June 2020

ER -

Zhang K, Gu S, Timofte R, Shang T, Dai Q, Zhu S et al. NTIRE 2020 challenge on perceptual extreme super-resolution: Methods and results. In Proceedings - 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2020. IEEE Computer Society. 2020. p. 2045-2057. 9150605. (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). doi: 10.1109/CVPRW50498.2020.00254

NTIRE 2020 challenge on perceptual extreme super-resolution: Methods and results

Abstract

Publication series

Conference

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this