NTIRE 2023 Challenge on Image Super-Resolution (×4): Methods and Results

Yulun Zhang; Kai Zhang; Zheng Chen; Yawei Li; Radu Timofte; Junpei Zhang; Kexin Zhang; Rui Peng; Yanbiao Ma; Licheng Jiao; Huaibo Huang; Xiaoqiang Zhou; Yuang Ai; Ran He; Yajun Qiu; Qiang Zhu; Pengfei Li; Qianhui Li; Shuyuan Zhu; Dafeng Zhang; Jia Li; Fan Wang; Chunmiao Li; Tae Hyung Kim; Jungkeong Kil; Eon Kim; Yeonseung Yu; Beomyeol Lee; Subin Lee; Seokjae Lim; Somi Chae; Heungjun Choi; Zhi Kai Huang; Yi Chung Chen; Yuan Chun Chiang; Hao Hsiang Yang; Wei Ting Chen; Hua En Chang; I. Hsiang Chen; Chia Hsuan Hsieh; Sy Yen Kuo; Ui Jin Choi; Marcos V. Conde; Sunder Ali Khowaja; Jiseok Yoon; Ik Hyun Lee; Garas Gendy; Nabil Sabor; Jingchao Hou; Guanghui He; Zhao Zhang; Baiang Li; Huan Zheng; Suiyi Zhao; Yangcheng Gao; Yanyan Wei; Jiahuan Ren; Jiayu Wei; Yanfeng Li; Jia Sun; Zhanyi Cheng; Zhiyuan Li; Xu Yao; Xinyi Wang; Danxu Li; Xuan Cui; Jun Cao; Cheng Li; Jianbin Zheng; Anjali Sarvaiya; Kalpesh Prajapati; Ratnadeep Patra; Pragnesh Barik; Chaitanya Rathod; Kishor Upla; Kiran Raja; Raghavendra Ramachandra; Christoph Busch

doi:10.1109/CVPRW59228.2023.00185

NTIRE 2023 Challenge on Image Super-Resolution (×4): Methods and Results

Yulun Zhang
, Kai Zhang
, Zheng Chen
, Yawei Li
, Radu Timofte
, Junpei Zhang
, Kexin Zhang
, Rui Peng
, Yanbiao Ma
, Licheng Jiao
, Huaibo Huang
, Xiaoqiang Zhou
, Yuang Ai
, Ran He
, Yajun Qiu
, Qiang Zhu
, Pengfei Li
, Qianhui Li
, Shuyuan Zhu
, Dafeng Zhang

Jia Li, Fan Wang, Chunmiao Li, Tae Hyung Kim, Jungkeong Kil, Eon Kim, Yeonseung Yu, Beomyeol Lee, Subin Lee, Seokjae Lim, Somi Chae, Heungjun Choi, Zhi Kai Huang, Yi Chung Chen, Yuan Chun Chiang, Hao Hsiang Yang, Wei Ting Chen, Hua En Chang, I. Hsiang Chen, Chia Hsuan Hsieh, Sy Yen Kuo, Ui Jin Choi, Marcos V. Conde, Sunder Ali Khowaja, Jiseok Yoon, Ik Hyun Lee, Garas Gendy, Nabil Sabor, Jingchao Hou, Guanghui He, Zhao Zhang, Baiang Li, Huan Zheng, Suiyi Zhao, Yangcheng Gao, Yanyan Wei, Jiahuan Ren, Jiayu Wei, Yanfeng Li, Jia Sun, Zhanyi Cheng, Zhiyuan Li, Xu Yao, Xinyi Wang, Danxu Li, Xuan Cui, Jun Cao, Cheng Li, Jianbin Zheng, Anjali Sarvaiya, Kalpesh Prajapati, Ratnadeep Patra, Pragnesh Barik, Chaitanya Rathod, Kishor Upla, Kiran Raja, Raghavendra Ramachandra, Christoph Busch

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

Abstract

This paper reviews the NTIRE 2023 challenge on image super-resolution (×4), focusing on the proposed solutions and results. The task of image super-resolution (SR) is to generate a high-resolution (HR) output from a corresponding low-resolution (LR) input by leveraging prior information from paired LR-HR images. The aim of the challenge is to obtain a network design/solution capable to produce high-quality results with the best performance (e.g., PSNR). We want to explore how high performance we can achieve regardless of computational cost (e.g., model size and FLOPs) and data. The track of the challenge was to measure the restored HR images with the ground truth HR images on DIV2K testing dataset. The ranking of the teams is determined directly by the PSNR value. The challenge has attracted 192 registered participants, where 15 teams made valid submissions. They achieve state-of-the-art performance in single image super-resolution.

Original language	English
Title of host publication	Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023
Publisher	IEEE Computer Society
Pages	1865-1884
Number of pages	20
ISBN (Electronic)	9798350302493
DOIs	https://doi.org/10.1109/CVPRW59228.2023.00185
Publication status	Published - 2023
Externally published	Yes
Event	2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023 - Vancouver, Canada Duration: 18 Jun 2023 → 22 Jun 2023

Publication series

Name	IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Volume	2023-June
ISSN (Print)	2160-7508
ISSN (Electronic)	2160-7516

Conference

Conference	2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023
Country/Territory	Canada
City	Vancouver
Period	18/06/23 → 22/06/23

Access to Document

10.1109/CVPRW59228.2023.00185

Cite this

Zhang, Y., Zhang, K., Chen, Z., Li, Y., Timofte, R., Zhang, J., Zhang, K., Peng, R., Ma, Y., Jiao, L., Huang, H., Zhou, X., Ai, Y., He, R., Qiu, Y., Zhu, Q., Li, P., Li, Q., Zhu, S., ... Busch, C. (2023). NTIRE 2023 Challenge on Image Super-Resolution (×4): Methods and Results. In Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023 (pp. 1865-1884). (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2023-June). IEEE Computer Society. https://doi.org/10.1109/CVPRW59228.2023.00185

@inproceedings{f5c5558efc4844eba52571db89ffe7ff,

title = "NTIRE 2023 Challenge on Image Super-Resolution (×4): Methods and Results",

abstract = "This paper reviews the NTIRE 2023 challenge on image super-resolution (×4), focusing on the proposed solutions and results. The task of image super-resolution (SR) is to generate a high-resolution (HR) output from a corresponding low-resolution (LR) input by leveraging prior information from paired LR-HR images. The aim of the challenge is to obtain a network design/solution capable to produce high-quality results with the best performance (e.g., PSNR). We want to explore how high performance we can achieve regardless of computational cost (e.g., model size and FLOPs) and data. The track of the challenge was to measure the restored HR images with the ground truth HR images on DIV2K testing dataset. The ranking of the teams is determined directly by the PSNR value. The challenge has attracted 192 registered participants, where 15 teams made valid submissions. They achieve state-of-the-art performance in single image super-resolution.",

author = "Yulun Zhang and Kai Zhang and Zheng Chen and Yawei Li and Radu Timofte and Junpei Zhang and Kexin Zhang and Rui Peng and Yanbiao Ma and Licheng Jiao and Huaibo Huang and Xiaoqiang Zhou and Yuang Ai and Ran He and Yajun Qiu and Qiang Zhu and Pengfei Li and Qianhui Li and Shuyuan Zhu and Dafeng Zhang and Jia Li and Fan Wang and Chunmiao Li and Kim, \{Tae Hyung\} and Jungkeong Kil and Eon Kim and Yeonseung Yu and Beomyeol Lee and Subin Lee and Seokjae Lim and Somi Chae and Heungjun Choi and Huang, \{Zhi Kai\} and Chen, \{Yi Chung\} and Chiang, \{Yuan Chun\} and Yang, \{Hao Hsiang\} and Chen, \{Wei Ting\} and Chang, \{Hua En\} and Chen, \{I. Hsiang\} and Hsieh, \{Chia Hsuan\} and Kuo, \{Sy Yen\} and Choi, \{Ui Jin\} and Conde, \{Marcos V.\} and Khowaja, \{Sunder Ali\} and Jiseok Yoon and Lee, \{Ik Hyun\} and Garas Gendy and Nabil Sabor and Jingchao Hou and Guanghui He and Zhao Zhang and Baiang Li and Huan Zheng and Suiyi Zhao and Yangcheng Gao and Yanyan Wei and Jiahuan Ren and Jiayu Wei and Yanfeng Li and Jia Sun and Zhanyi Cheng and Zhiyuan Li and Xu Yao and Xinyi Wang and Danxu Li and Xuan Cui and Jun Cao and Cheng Li and Jianbin Zheng and Anjali Sarvaiya and Kalpesh Prajapati and Ratnadeep Patra and Pragnesh Barik and Chaitanya Rathod and Kishor Upla and Kiran Raja and Raghavendra Ramachandra and Christoph Busch",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023 ; Conference date: 18-06-2023 Through 22-06-2023",

year = "2023",

doi = "10.1109/CVPRW59228.2023.00185",

language = "English",

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

publisher = "IEEE Computer Society",

pages = "1865--1884",

booktitle = "Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023",

address = "United States",

}

Zhang, Y, Zhang, K, Chen, Z, Li, Y, Timofte, R, Zhang, J, Zhang, K, Peng, R, Ma, Y, Jiao, L, Huang, H, Zhou, X, Ai, Y, He, R, Qiu, Y, Zhu, Q, Li, P, Li, Q, Zhu, S, Zhang, D, Li, J, Wang, F, Li, C, Kim, TH, Kil, J, Kim, E, Yu, Y, Lee, B, Lee, S, Lim, S, Chae, S, Choi, H, Huang, ZK, Chen, YC, Chiang, YC, Yang, HH, Chen, WT, Chang, HE, Chen, IH, Hsieh, CH, Kuo, SY, Choi, UJ, Conde, MV, Khowaja, SA, Yoon, J, Lee, IH, Gendy, G, Sabor, N, Hou, J, He, G, Zhang, Z, Li, B, Zheng, H, Zhao, S, Gao, Y, Wei, Y, Ren, J, Wei, J, Li, Y, Sun, J, Cheng, Z, Li, Z, Yao, X, Wang, X, Li, D, Cui, X, Cao, J, Li, C, Zheng, J, Sarvaiya, A, Prajapati, K, Patra, R, Barik, P, Rathod, C, Upla, K, Raja, K, Ramachandra, R & Busch, C 2023, NTIRE 2023 Challenge on Image Super-Resolution (×4): Methods and Results. in Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, vol. 2023-June, IEEE Computer Society, pp. 1865-1884, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023, Vancouver, Canada, 18/06/23. https://doi.org/10.1109/CVPRW59228.2023.00185

NTIRE 2023 Challenge on Image Super-Resolution (×4): Methods and Results. / Zhang, Yulun; Zhang, Kai; Chen, Zheng et al.
Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023. IEEE Computer Society, 2023. p. 1865-1884 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2023-June).

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

TY - GEN

T1 - NTIRE 2023 Challenge on Image Super-Resolution (×4)

T2 - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023

AU - Zhang, Yulun

AU - Zhang, Kai

AU - Chen, Zheng

AU - Li, Yawei

AU - Timofte, Radu

AU - Zhang, Junpei

AU - Zhang, Kexin

AU - Peng, Rui

AU - Ma, Yanbiao

AU - Jiao, Licheng

AU - Huang, Huaibo

AU - Zhou, Xiaoqiang

AU - Ai, Yuang

AU - He, Ran

AU - Qiu, Yajun

AU - Zhu, Qiang

AU - Li, Pengfei

AU - Li, Qianhui

AU - Zhu, Shuyuan

AU - Zhang, Dafeng

AU - Li, Jia

AU - Wang, Fan

AU - Li, Chunmiao

AU - Kim, Tae Hyung

AU - Kil, Jungkeong

AU - Kim, Eon

AU - Yu, Yeonseung

AU - Lee, Beomyeol

AU - Lee, Subin

AU - Lim, Seokjae

AU - Chae, Somi

AU - Choi, Heungjun

AU - Huang, Zhi Kai

AU - Chen, Yi Chung

AU - Chiang, Yuan Chun

AU - Yang, Hao Hsiang

AU - Chen, Wei Ting

AU - Chang, Hua En

AU - Chen, I. Hsiang

AU - Hsieh, Chia Hsuan

AU - Kuo, Sy Yen

AU - Choi, Ui Jin

AU - Conde, Marcos V.

AU - Khowaja, Sunder Ali

AU - Yoon, Jiseok

AU - Lee, Ik Hyun

AU - Gendy, Garas

AU - Sabor, Nabil

AU - Hou, Jingchao

AU - He, Guanghui

AU - Zhang, Zhao

AU - Li, Baiang

AU - Zheng, Huan

AU - Zhao, Suiyi

AU - Gao, Yangcheng

AU - Wei, Yanyan

AU - Ren, Jiahuan

AU - Wei, Jiayu

AU - Li, Yanfeng

AU - Sun, Jia

AU - Cheng, Zhanyi

AU - Li, Zhiyuan

AU - Yao, Xu

AU - Wang, Xinyi

AU - Li, Danxu

AU - Cui, Xuan

AU - Cao, Jun

AU - Li, Cheng

AU - Zheng, Jianbin

AU - Sarvaiya, Anjali

AU - Prajapati, Kalpesh

AU - Patra, Ratnadeep

AU - Barik, Pragnesh

AU - Rathod, Chaitanya

AU - Upla, Kishor

AU - Raja, Kiran

AU - Ramachandra, Raghavendra

AU - Busch, Christoph

PY - 2023

Y1 - 2023

N2 - This paper reviews the NTIRE 2023 challenge on image super-resolution (×4), focusing on the proposed solutions and results. The task of image super-resolution (SR) is to generate a high-resolution (HR) output from a corresponding low-resolution (LR) input by leveraging prior information from paired LR-HR images. The aim of the challenge is to obtain a network design/solution capable to produce high-quality results with the best performance (e.g., PSNR). We want to explore how high performance we can achieve regardless of computational cost (e.g., model size and FLOPs) and data. The track of the challenge was to measure the restored HR images with the ground truth HR images on DIV2K testing dataset. The ranking of the teams is determined directly by the PSNR value. The challenge has attracted 192 registered participants, where 15 teams made valid submissions. They achieve state-of-the-art performance in single image super-resolution.

AB - This paper reviews the NTIRE 2023 challenge on image super-resolution (×4), focusing on the proposed solutions and results. The task of image super-resolution (SR) is to generate a high-resolution (HR) output from a corresponding low-resolution (LR) input by leveraging prior information from paired LR-HR images. The aim of the challenge is to obtain a network design/solution capable to produce high-quality results with the best performance (e.g., PSNR). We want to explore how high performance we can achieve regardless of computational cost (e.g., model size and FLOPs) and data. The track of the challenge was to measure the restored HR images with the ground truth HR images on DIV2K testing dataset. The ranking of the teams is determined directly by the PSNR value. The challenge has attracted 192 registered participants, where 15 teams made valid submissions. They achieve state-of-the-art performance in single image super-resolution.

UR - https://www.scopus.com/pages/publications/85168271943

U2 - 10.1109/CVPRW59228.2023.00185

DO - 10.1109/CVPRW59228.2023.00185

M3 - Conference contribution

AN - SCOPUS:85168271943

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

SP - 1865

EP - 1884

BT - Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023

PB - IEEE Computer Society

Y2 - 18 June 2023 through 22 June 2023

ER -

Zhang Y, Zhang K, Chen Z, Li Y, Timofte R, Zhang J et al. NTIRE 2023 Challenge on Image Super-Resolution (×4): Methods and Results. In Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023. IEEE Computer Society. 2023. p. 1865-1884. (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). doi: 10.1109/CVPRW59228.2023.00185

NTIRE 2023 Challenge on Image Super-Resolution (×4): Methods and Results

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this