NTIRE 2021 learning the super-resolution space challenge

Andreas Lugmayr; Martin Danelljan; Radu Timofte; Christoph Busch; Yang Chen; Jian Cheng; Vishal Chudasama; Ruipeng Gang; Shangqi Gao; Kun Gao; Laiyun Gong; Qingrui Han; Chao Huang; Zhi Jin; Younghyun Jo; Seon Joo Kim; Younggeun Kim; Seungjun Lee; Yuchen Lei; Chu Tak Li; Chenghua Li; Ke Li; Zhi Song Liu; Youming Liu; Nan Nan; Seung Ho Park; Heena Patel; Shichong Peng; Kalpesh Prajapati; Haoran Qi; Kiran Raja; Raghavendra Ramachandra; Wan Chi Siu; Donghee Son; Ruixia Song; Kishor Upla; Li Wen Wang; Yatian Wang; Junwei Wang; Qianyu Wu; Xinhua Xu; Sejong Yang; Zhen Yuan; Liting Zhang; Huanrong Zhang; Junkai Zhang; Yifan Zhang; Zhenzhou Zhang; Hangqi Zhou; Aichun Zhu; Xiahai Zhuang; Jiaxin Zou

doi:10.1109/CVPRW53098.2021.00072

NTIRE 2021 learning the super-resolution space challenge

Andreas Lugmayr, Martin Danelljan, Radu Timofte, Christoph Busch, Yang Chen, Jian Cheng, Vishal Chudasama, Ruipeng Gang, Shangqi Gao, Kun Gao, Laiyun Gong, Qingrui Han, Chao Huang, Zhi Jin, Younghyun Jo, Seon Joo Kim, Younggeun Kim, Seungjun Lee, Yuchen Lei, Chu Tak LiChenghua Li, Ke Li, Zhi Song Liu, Youming Liu, Nan Nan, Seung Ho Park, Heena Patel, Shichong Peng, Kalpesh Prajapati, Haoran Qi, Kiran Raja, Raghavendra Ramachandra, Wan Chi Siu, Donghee Son, Ruixia Song, Kishor Upla, Li Wen Wang, Yatian Wang, Junwei Wang, Qianyu Wu, Xinhua Xu, Sejong Yang, Zhen Yuan, Liting Zhang, Huanrong Zhang, Junkai Zhang, Yifan Zhang, Zhenzhou Zhang, Hangqi Zhou, Aichun Zhu, Xiahai Zhuang, Jiaxin Zou

College of Computing

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

29 Citations (Scopus)

Abstract

This paper reviews the NTIRE 2021 challenge on learning the super-Resolution space. It focuses on the participating methods and final results. The challenge addresses the problem of learning a model capable of predicting the space of plausible super-resolution (SR) images, from a single low-resolution image. The model must thus be capable of sampling diverse outputs, rather than just generating a single SR image. The goal of the challenge is to spur research into developing learning formulations and models better suited for the highly ill-posed SR problem. And thereby advance the state-of-the-art in the broader SR field. In order to evaluate the quality of the predicted SR space, we propose a new evaluation metric and perform a comprehensive analysis of the participating methods. The challenge contains two tracks: 4× and 8 scale factor. In total, 11 teams competed in the final testing× phase.

Original language	English
Title of host publication	Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021
Publisher	IEEE Computer Society
Pages	596-612
Number of pages	17
ISBN (Electronic)	9781665448994
DOIs	https://doi.org/10.1109/CVPRW53098.2021.00072
Publication status	Published - 2021 Jun
Event	2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021 - Virtual, Online, United States Duration: 2021 Jun 19 → 2021 Jun 25

Publication series

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

Conference

Conference	2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021
Country/Territory	United States
City	Virtual, Online
Period	21/6/19 → 21/6/25

Bibliographical note

Publisher Copyright:
© 2021 IEEE.

All Science Journal Classification (ASJC) codes

Computer Vision and Pattern Recognition
Electrical and Electronic Engineering

Access to Document

10.1109/CVPRW53098.2021.00072

Cite this

Lugmayr, A., Danelljan, M., Timofte, R., Busch, C., Chen, Y., Cheng, J., Chudasama, V., Gang, R., Gao, S., Gao, K., Gong, L., Han, Q., Huang, C., Jin, Z., Jo, Y., Kim, S. J., Kim, Y., Lee, S., Lei, Y., ... Zou, J. (2021). NTIRE 2021 learning the super-resolution space challenge. In Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021 (pp. 596-612). (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). IEEE Computer Society. https://doi.org/10.1109/CVPRW53098.2021.00072

@inproceedings{c48f1b09dba549ea90edf95a3e8b2a98,

title = "NTIRE 2021 learning the super-resolution space challenge",

abstract = "This paper reviews the NTIRE 2021 challenge on learning the super-Resolution space. It focuses on the participating methods and final results. The challenge addresses the problem of learning a model capable of predicting the space of plausible super-resolution (SR) images, from a single low-resolution image. The model must thus be capable of sampling diverse outputs, rather than just generating a single SR image. The goal of the challenge is to spur research into developing learning formulations and models better suited for the highly ill-posed SR problem. And thereby advance the state-of-the-art in the broader SR field. In order to evaluate the quality of the predicted SR space, we propose a new evaluation metric and perform a comprehensive analysis of the participating methods. The challenge contains two tracks: 4× and 8 scale factor. In total, 11 teams competed in the final testing× phase.",

author = "Andreas Lugmayr and Martin Danelljan and Radu Timofte and Christoph Busch and Yang Chen and Jian Cheng and Vishal Chudasama and Ruipeng Gang and Shangqi Gao and Kun Gao and Laiyun Gong and Qingrui Han and Chao Huang and Zhi Jin and Younghyun Jo and Kim, {Seon Joo} and Younggeun Kim and Seungjun Lee and Yuchen Lei and Li, {Chu Tak} and Chenghua Li and Ke Li and Liu, {Zhi Song} and Youming Liu and Nan Nan and Park, {Seung Ho} and Heena Patel and Shichong Peng and Kalpesh Prajapati and Haoran Qi and Kiran Raja and Raghavendra Ramachandra and Siu, {Wan Chi} and Donghee Son and Ruixia Song and Kishor Upla and Wang, {Li Wen} and Yatian Wang and Junwei Wang and Qianyu Wu and Xinhua Xu and Sejong Yang and Zhen Yuan and Liting Zhang and Huanrong Zhang and Junkai Zhang and Yifan Zhang and Zhenzhou Zhang and Hangqi Zhou and Aichun Zhu and Xiahai Zhuang and Jiaxin Zou",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021 ; Conference date: 19-06-2021 Through 25-06-2021",

year = "2021",

month = jun,

doi = "10.1109/CVPRW53098.2021.00072",

language = "English",

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

publisher = "IEEE Computer Society",

pages = "596--612",

booktitle = "Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021",

address = "United States",

}

Lugmayr, A, Danelljan, M, Timofte, R, Busch, C, Chen, Y, Cheng, J, Chudasama, V, Gang, R, Gao, S, Gao, K, Gong, L, Han, Q, Huang, C, Jin, Z, Jo, Y, Kim, SJ, Kim, Y, Lee, S, Lei, Y, Li, CT, Li, C, Li, K, Liu, ZS, Liu, Y, Nan, N, Park, SH, Patel, H, Peng, S, Prajapati, K, Qi, H, Raja, K, Ramachandra, R, Siu, WC, Son, D, Song, R, Upla, K, Wang, LW, Wang, Y, Wang, J, Wu, Q, Xu, X, Yang, S, Yuan, Z, Zhang, L, Zhang, H, Zhang, J, Zhang, Y, Zhang, Z, Zhou, H, Zhu, A, Zhuang, X & Zou, J 2021, NTIRE 2021 learning the super-resolution space challenge. in Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, IEEE Computer Society, pp. 596-612, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021, Virtual, Online, United States, 21/6/19. https://doi.org/10.1109/CVPRW53098.2021.00072

NTIRE 2021 learning the super-resolution space challenge. / Lugmayr, Andreas; Danelljan, Martin; Timofte, Radu et al.
Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021. IEEE Computer Society, 2021. p. 596-612 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops).

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

TY - GEN

T1 - NTIRE 2021 learning the super-resolution space challenge

AU - Lugmayr, Andreas

AU - Danelljan, Martin

AU - Timofte, Radu

AU - Busch, Christoph

AU - Chen, Yang

AU - Cheng, Jian

AU - Chudasama, Vishal

AU - Gang, Ruipeng

AU - Gao, Shangqi

AU - Gao, Kun

AU - Gong, Laiyun

AU - Han, Qingrui

AU - Huang, Chao

AU - Jin, Zhi

AU - Jo, Younghyun

AU - Kim, Seon Joo

AU - Kim, Younggeun

AU - Lee, Seungjun

AU - Lei, Yuchen

AU - Li, Chu Tak

AU - Li, Chenghua

AU - Li, Ke

AU - Liu, Zhi Song

AU - Liu, Youming

AU - Nan, Nan

AU - Park, Seung Ho

AU - Patel, Heena

AU - Peng, Shichong

AU - Prajapati, Kalpesh

AU - Qi, Haoran

AU - Raja, Kiran

AU - Ramachandra, Raghavendra

AU - Siu, Wan Chi

AU - Son, Donghee

AU - Song, Ruixia

AU - Upla, Kishor

AU - Wang, Li Wen

AU - Wang, Yatian

AU - Wang, Junwei

AU - Wu, Qianyu

AU - Xu, Xinhua

AU - Yang, Sejong

AU - Yuan, Zhen

AU - Zhang, Liting

AU - Zhang, Huanrong

AU - Zhang, Junkai

AU - Zhang, Yifan

AU - Zhang, Zhenzhou

AU - Zhou, Hangqi

AU - Zhu, Aichun

AU - Zhuang, Xiahai

AU - Zou, Jiaxin

PY - 2021/6

Y1 - 2021/6

N2 - This paper reviews the NTIRE 2021 challenge on learning the super-Resolution space. It focuses on the participating methods and final results. The challenge addresses the problem of learning a model capable of predicting the space of plausible super-resolution (SR) images, from a single low-resolution image. The model must thus be capable of sampling diverse outputs, rather than just generating a single SR image. The goal of the challenge is to spur research into developing learning formulations and models better suited for the highly ill-posed SR problem. And thereby advance the state-of-the-art in the broader SR field. In order to evaluate the quality of the predicted SR space, we propose a new evaluation metric and perform a comprehensive analysis of the participating methods. The challenge contains two tracks: 4× and 8 scale factor. In total, 11 teams competed in the final testing× phase.

AB - This paper reviews the NTIRE 2021 challenge on learning the super-Resolution space. It focuses on the participating methods and final results. The challenge addresses the problem of learning a model capable of predicting the space of plausible super-resolution (SR) images, from a single low-resolution image. The model must thus be capable of sampling diverse outputs, rather than just generating a single SR image. The goal of the challenge is to spur research into developing learning formulations and models better suited for the highly ill-posed SR problem. And thereby advance the state-of-the-art in the broader SR field. In order to evaluate the quality of the predicted SR space, we propose a new evaluation metric and perform a comprehensive analysis of the participating methods. The challenge contains two tracks: 4× and 8 scale factor. In total, 11 teams competed in the final testing× phase.

UR - http://www.scopus.com/inward/record.url?scp=85108400229&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85108400229&partnerID=8YFLogxK

U2 - 10.1109/CVPRW53098.2021.00072

DO - 10.1109/CVPRW53098.2021.00072

M3 - Conference contribution

AN - SCOPUS:85108400229

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

SP - 596

EP - 612

BT - Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021

PB - IEEE Computer Society

T2 - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021

Y2 - 19 June 2021 through 25 June 2021

ER -

Lugmayr A, Danelljan M, Timofte R, Busch C, Chen Y, Cheng J et al. NTIRE 2021 learning the super-resolution space challenge. In Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2021. IEEE Computer Society. 2021. p. 596-612. (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). doi: 10.1109/CVPRW53098.2021.00072

NTIRE 2021 learning the super-resolution space challenge

Abstract

Publication series

Conference

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this