NTIRE 2023 Challenge on Efficient Super-Resolution: Methods and Results

Yawei Li; Yulun Zhang; Radu Timofte; Luc Van Gool; Lei Yu; Youwei Li; Xinpeng Li; Ting Jiang; Qi Wu; Mingyan Han; Wenjie Lin; Chengzhi Jiang; Jinting Luo; Haoqiang Fan; Shuaicheng Liu; Yucong Wang; Minjie Cai; Mingxi Li; Yuhang Zhang; Xian Jun Fan; Yankai Sheng; Yanyu Mao; Nihao Zhang; Qian Wang; Mingjun Zheng; Long Sun; Jinshan Pan; Jiangxin Dong; Jinhui Tang; Zhongbao Yang; Yan Wang; Erlin Pan; Qixuan Cai; Xinan Dai; Magauiya Zhussip; Nikolay Kalyazin; Dmitry Vyal; Xueyi Zou; Youliang Yan; Heaseo Chung; Jin Zhang; Gaocheng Yu; Feng Zhang; Hongbin Wang; Bohao Liao; Zhibo Du; Yu Liang Wu; Gege Shi; Long Peng; Yang Wang; Yang Cao; Zhengjun Zha; 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; Xin Liu; Jiahao Pan; Hongyuan Yu; Weichen Yu; Lin Ge; Jiahua Dong; Yajun Zou; Zhuoyuan Wu; Binnan Han; Xiaolin Zhang; Heng Zhang; Xuanwu Yin; Kunlong Zuo; Weijian Deng; Hongjie Yuan; Zengtong Lu; Mingyu Ouyang; Wenzhuo Ma; Nian Liu; Hanyou Zheng; Yuantong Zhang; Junxi Zhang; Zhenzhong Chen; Garas Gendy; Nabil Sabor; Jingchao Hou; Guanghui He; Yurui Zhu; Xi Wang; Xueyang Fu; Zheng Jun Zha; Daheng Yin; Mengyang Liu; Baijun Chen; Ao Li; Lei Luo; Kangjun Jin; Ce Zhu; Xiaoming Zhang; Chengxing Xie; Linze Li; Haiteng Meng; Tianlin Zhang; Tianrui Li; Xiaole Zhao; Zhao Zhang; Baiang Li; Huan Zheng; Suiyi Zhao; Yangcheng Gao; Jiahuan Ren; Kang Hu; Jingpeng Shi; Zhijian Wu; Dingjiang Huang; Jinchen Zhu; Hui Li; Qianru Xv; Tianle Liu; Shizhuang Weng; Gang Wu; Junpeng Jiang; Xianming Liu; Junjun Jiang; Mingjian Zhang; Jing Hu; Chengxu Wu; Qinrui Fan; Chengming Feng; Ziwei Luo; Shu Hu; Siwei Lyu; Xi Wu; Xin Wang

doi:10.1109/CVPRW59228.2023.00189

NTIRE 2023 Challenge on Efficient Super-Resolution: Methods and Results

Yawei Li^*
, Yulun Zhang
, Radu Timofte
, Luc Van Gool
, Lei Yu
, Youwei Li
, Xinpeng Li
, Ting Jiang
, Qi Wu
, Mingyan Han
, Wenjie Lin
, Chengzhi Jiang
, Jinting Luo
, Haoqiang Fan
, Shuaicheng Liu
, Yucong Wang
, Minjie Cai
, Mingxi Li
, Yuhang Zhang
, Xian Jun Fan

Yankai Sheng, Yanyu Mao, Nihao Zhang, Qian Wang, Mingjun Zheng, Long Sun, Jinshan Pan, Jiangxin Dong, Jinhui Tang, Zhongbao Yang, Yan Wang, Erlin Pan, Qixuan Cai, Xinan Dai, Magauiya Zhussip, Nikolay Kalyazin, Dmitry Vyal, Xueyi Zou, Youliang Yan, Heaseo Chung, Jin Zhang, Gaocheng Yu, Feng Zhang, Hongbin Wang, Bohao Liao, Zhibo Du, Yu Liang Wu, Gege Shi, Long Peng, Yang Wang, Yang Cao, Zhengjun Zha, 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, Xin Liu, Jiahao Pan, Hongyuan Yu, Weichen Yu, Lin Ge, Jiahua Dong, Yajun Zou, Zhuoyuan Wu, Binnan Han, Xiaolin Zhang, Heng Zhang, Xuanwu Yin, Kunlong Zuo, Weijian Deng, Hongjie Yuan, Zengtong Lu, Mingyu Ouyang, Wenzhuo Ma, Nian Liu, Hanyou Zheng, Yuantong Zhang, Junxi Zhang, Zhenzhong Chen, Garas Gendy, Nabil Sabor, Jingchao Hou, Guanghui He, Yurui Zhu, Xi Wang, Xueyang Fu, Zheng Jun Zha, Daheng Yin, Mengyang Liu, Baijun Chen, Ao Li, Lei Luo, Kangjun Jin, Ce Zhu, Xiaoming Zhang, Chengxing Xie, Linze Li, Haiteng Meng, Tianlin Zhang, Tianrui Li, Xiaole Zhao, Zhao Zhang, Baiang Li, Huan Zheng, Suiyi Zhao, Yangcheng Gao, Jiahuan Ren, Kang Hu, Jingpeng Shi, Zhijian Wu, Dingjiang Huang, Jinchen Zhu, Hui Li, Qianru Xv, Tianle Liu, Shizhuang Weng, Gang Wu, Junpeng Jiang, Xianming Liu, Junjun Jiang, Mingjian Zhang, Jing Hu, Chengxu Wu, Qinrui Fan, Chengming Feng, Ziwei Luo, Shu Hu, Siwei Lyu, Xi Wu, Xin Wang

^*Corresponding author for this work

School of Data Science and Engineering

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

82 Scopus citations

Abstract

This paper reviews the NTIRE 2023 challenge on efficient single-image super-resolution with a focus on the proposed solutions and results. The aim of this challenge is to devise a network that reduces one or several aspects such as runtime, parameters, FLOPs, activations, memory footprint, and depth of RFDN while at least maintaining the PSNR of 29.00dB on DIV2K validation datasets. The challenge had 272 registered participants, and 35 teams made valid submissions. They gauge the state-of-the-art for efficient 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	1922-1960
Number of pages	39
ISBN (Electronic)	9798350302493
DOIs	https://doi.org/10.1109/CVPRW59228.2023.00189
State	Published - 2023
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/CVPRW59228.2023.00189

Cite this

Li, Y., Zhang, Y., Timofte, R., Van Gool, L., Yu, L., Li, Y., Li, X., Jiang, T., Wu, Q., Han, M., Lin, W., Jiang, C., Luo, J., Fan, H., Liu, S., Wang, Y., Cai, M., Li, M., Zhang, Y., ... Wang, X. (2023). NTIRE 2023 Challenge on Efficient Super-Resolution: Methods and Results. In Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023 (pp. 1922-1960). (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2023-June). IEEE Computer Society. https://doi.org/10.1109/CVPRW59228.2023.00189

@inproceedings{506d542ab6304290a56122baa8f43b43,

title = "NTIRE 2023 Challenge on Efficient Super-Resolution: Methods and Results",

abstract = "This paper reviews the NTIRE 2023 challenge on efficient single-image super-resolution with a focus on the proposed solutions and results. The aim of this challenge is to devise a network that reduces one or several aspects such as runtime, parameters, FLOPs, activations, memory footprint, and depth of RFDN while at least maintaining the PSNR of 29.00dB on DIV2K validation datasets. The challenge had 272 registered participants, and 35 teams made valid submissions. They gauge the state-of-the-art for efficient single-image super-resolution.",

author = "Yawei Li and Yulun Zhang and Radu Timofte and \{Van Gool\}, Luc and Lei Yu and Youwei Li and Xinpeng Li and Ting Jiang and Qi Wu and Mingyan Han and Wenjie Lin and Chengzhi Jiang and Jinting Luo and Haoqiang Fan and Shuaicheng Liu and Yucong Wang and Minjie Cai and Mingxi Li and Yuhang Zhang and Fan, \{Xian Jun\} and Yankai Sheng and Yanyu Mao and Nihao Zhang and Qian Wang and Mingjun Zheng and Long Sun and Jinshan Pan and Jiangxin Dong and Jinhui Tang and Zhongbao Yang and Yan Wang and Erlin Pan and Qixuan Cai and Xinan Dai and Magauiya Zhussip and Nikolay Kalyazin and Dmitry Vyal and Xueyi Zou and Youliang Yan and Heaseo Chung and Jin Zhang and Gaocheng Yu and Feng Zhang and Hongbin Wang and Bohao Liao and Zhibo Du and Wu, \{Yu Liang\} and Gege Shi and Long Peng and Yang Wang and Yang Cao and Zhengjun Zha 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 Xin Liu and Jiahao Pan and Hongyuan Yu and Weichen Yu and Lin Ge and Jiahua Dong and Yajun Zou and Zhuoyuan Wu and Binnan Han and Xiaolin Zhang and Heng Zhang and Xuanwu Yin and Kunlong Zuo and Weijian Deng and Hongjie Yuan and Zengtong Lu and Mingyu Ouyang and Wenzhuo Ma and Nian Liu and Hanyou Zheng and Yuantong Zhang and Junxi Zhang and Zhenzhong Chen and Garas Gendy and Nabil Sabor and Jingchao Hou and Guanghui He and Yurui Zhu and Xi Wang and Xueyang Fu and Zha, \{Zheng Jun\} and Daheng Yin and Mengyang Liu and Baijun Chen and Ao Li and Lei Luo and Kangjun Jin and Ce Zhu and Xiaoming Zhang and Chengxing Xie and Linze Li and Haiteng Meng and Tianlin Zhang and Tianrui Li and Xiaole Zhao and Zhao Zhang and Baiang Li and Huan Zheng and Suiyi Zhao and Yangcheng Gao and Jiahuan Ren and Kang Hu and Jingpeng Shi and Zhijian Wu and Dingjiang Huang and Jinchen Zhu and Hui Li and Qianru Xv and Tianle Liu and Shizhuang Weng and Gang Wu and Junpeng Jiang and Xianming Liu and Junjun Jiang and Mingjian Zhang and Jing Hu and Chengxu Wu and Qinrui Fan and Chengming Feng and Ziwei Luo and Shu Hu and Siwei Lyu and Xi Wu and Xin Wang",

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/CVPRW59228.2023.00189",

language = "英语",

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

publisher = "IEEE Computer Society",

pages = "1922--1960",

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

address = "美国",

}

Li, Y, Zhang, Y, Timofte, R, Van Gool, L, Yu, L, Li, Y, Li, X, Jiang, T, Wu, Q, Han, M, Lin, W, Jiang, C, Luo, J, Fan, H, Liu, S, Wang, Y, Cai, M, Li, M, Zhang, Y, Fan, XJ, Sheng, Y, Mao, Y, Zhang, N, Wang, Q, Zheng, M, Sun, L, Pan, J, Dong, J, Tang, J, Yang, Z, Wang, Y, Pan, E, Cai, Q, Dai, X, Zhussip, M, Kalyazin, N, Vyal, D, Zou, X, Yan, Y, Chung, H, Zhang, J, Yu, G, Zhang, F, Wang, H, Liao, B, Du, Z, Wu, YL, Shi, G, Peng, L, Wang, Y, Cao, Y, Zha, Z, Huang, ZK, Chen, YC, Chiang, YC, Yang, HH, Chen, WT, Chang, HE, Chen, IH, Hsieh, CH, Kuo, SY, Liu, X, Pan, J, Yu, H, Yu, W, Ge, L, Dong, J, Zou, Y, Wu, Z, Han, B, Zhang, X, Zhang, H, Yin, X, Zuo, K, Deng, W, Yuan, H, Lu, Z, Ouyang, M, Ma, W, Liu, N, Zheng, H, Zhang, Y, Zhang, J, Chen, Z, Gendy, G, Sabor, N, Hou, J, He, G, Zhu, Y, Wang, X, Fu, X, Zha, ZJ, Yin, D, Liu, M, Chen, B, Li, A, Luo, L, Jin, K, Zhu, C, Zhang, X, Xie, C, Li, L, Meng, H, Zhang, T, Li, T, Zhao, X, Zhang, Z, Li, B, Zheng, H, Zhao, S, Gao, Y, Ren, J, Hu, K, Shi, J, Wu, Z, Huang, D, Zhu, J, Li, H, Xv, Q, Liu, T, Weng, S, Wu, G, Jiang, J, Liu, X, Jiang, J, Zhang, M, Hu, J, Wu, C, Fan, Q, Feng, C, Luo, Z, Hu, S, Lyu, S, Wu, X & Wang, X 2023, NTIRE 2023 Challenge on Efficient Super-Resolution: 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. 1922-1960, 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023, Vancouver, Canada, 18/06/23. https://doi.org/10.1109/CVPRW59228.2023.00189

NTIRE 2023 Challenge on Efficient Super-Resolution: Methods and Results. / Li, Yawei; Zhang, Yulun; Timofte, Radu et al.
Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023. IEEE Computer Society, 2023. p. 1922-1960 (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 Efficient Super-Resolution

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

AU - Li, Yawei

AU - Zhang, Yulun

AU - Timofte, Radu

AU - Van Gool, Luc

AU - Yu, Lei

AU - Li, Youwei

AU - Li, Xinpeng

AU - Jiang, Ting

AU - Wu, Qi

AU - Han, Mingyan

AU - Lin, Wenjie

AU - Jiang, Chengzhi

AU - Luo, Jinting

AU - Fan, Haoqiang

AU - Liu, Shuaicheng

AU - Wang, Yucong

AU - Cai, Minjie

AU - Li, Mingxi

AU - Zhang, Yuhang

AU - Fan, Xian Jun

AU - Sheng, Yankai

AU - Mao, Yanyu

AU - Zhang, Nihao

AU - Wang, Qian

AU - Zheng, Mingjun

AU - Sun, Long

AU - Pan, Jinshan

AU - Dong, Jiangxin

AU - Tang, Jinhui

AU - Yang, Zhongbao

AU - Wang, Yan

AU - Pan, Erlin

AU - Cai, Qixuan

AU - Dai, Xinan

AU - Zhussip, Magauiya

AU - Kalyazin, Nikolay

AU - Vyal, Dmitry

AU - Zou, Xueyi

AU - Yan, Youliang

AU - Chung, Heaseo

AU - Zhang, Jin

AU - Yu, Gaocheng

AU - Zhang, Feng

AU - Wang, Hongbin

AU - Liao, Bohao

AU - Du, Zhibo

AU - Wu, Yu Liang

AU - Shi, Gege

AU - Peng, Long

AU - Wang, Yang

AU - Cao, Yang

AU - Zha, Zhengjun

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 - Liu, Xin

AU - Pan, Jiahao

AU - Yu, Hongyuan

AU - Yu, Weichen

AU - Ge, Lin

AU - Dong, Jiahua

AU - Zou, Yajun

AU - Wu, Zhuoyuan

AU - Han, Binnan

AU - Zhang, Xiaolin

AU - Zhang, Heng

AU - Yin, Xuanwu

AU - Zuo, Kunlong

AU - Deng, Weijian

AU - Yuan, Hongjie

AU - Lu, Zengtong

AU - Ouyang, Mingyu

AU - Ma, Wenzhuo

AU - Liu, Nian

AU - Zheng, Hanyou

AU - Zhang, Yuantong

AU - Zhang, Junxi

AU - Chen, Zhenzhong

AU - Gendy, Garas

AU - Sabor, Nabil

AU - Hou, Jingchao

AU - He, Guanghui

AU - Zhu, Yurui

AU - Wang, Xi

AU - Fu, Xueyang

AU - Zha, Zheng Jun

AU - Yin, Daheng

AU - Liu, Mengyang

AU - Chen, Baijun

AU - Li, Ao

AU - Luo, Lei

AU - Jin, Kangjun

AU - Zhu, Ce

AU - Zhang, Xiaoming

AU - Xie, Chengxing

AU - Li, Linze

AU - Meng, Haiteng

AU - Zhang, Tianlin

AU - Li, Tianrui

AU - Zhao, Xiaole

AU - Zhang, Zhao

AU - Li, Baiang

AU - Zheng, Huan

AU - Zhao, Suiyi

AU - Gao, Yangcheng

AU - Ren, Jiahuan

AU - Hu, Kang

AU - Shi, Jingpeng

AU - Wu, Zhijian

AU - Huang, Dingjiang

AU - Zhu, Jinchen

AU - Li, Hui

AU - Xv, Qianru

AU - Liu, Tianle

AU - Weng, Shizhuang

AU - Wu, Gang

AU - Jiang, Junpeng

AU - Liu, Xianming

AU - Jiang, Junjun

AU - Zhang, Mingjian

AU - Hu, Jing

AU - Wu, Chengxu

AU - Fan, Qinrui

AU - Feng, Chengming

AU - Luo, Ziwei

AU - Hu, Shu

AU - Lyu, Siwei

AU - Wu, Xi

AU - Wang, Xin

PY - 2023

Y1 - 2023

N2 - This paper reviews the NTIRE 2023 challenge on efficient single-image super-resolution with a focus on the proposed solutions and results. The aim of this challenge is to devise a network that reduces one or several aspects such as runtime, parameters, FLOPs, activations, memory footprint, and depth of RFDN while at least maintaining the PSNR of 29.00dB on DIV2K validation datasets. The challenge had 272 registered participants, and 35 teams made valid submissions. They gauge the state-of-the-art for efficient single-image super-resolution.

AB - This paper reviews the NTIRE 2023 challenge on efficient single-image super-resolution with a focus on the proposed solutions and results. The aim of this challenge is to devise a network that reduces one or several aspects such as runtime, parameters, FLOPs, activations, memory footprint, and depth of RFDN while at least maintaining the PSNR of 29.00dB on DIV2K validation datasets. The challenge had 272 registered participants, and 35 teams made valid submissions. They gauge the state-of-the-art for efficient single-image super-resolution.

UR - https://www.scopus.com/pages/publications/85159428940

U2 - 10.1109/CVPRW59228.2023.00189

DO - 10.1109/CVPRW59228.2023.00189

M3 - 会议稿件

AN - SCOPUS:85159428940

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

SP - 1922

EP - 1960

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 -

Li Y, Zhang Y, Timofte R, Van Gool L, Yu L, Li Y et al. NTIRE 2023 Challenge on Efficient Super-Resolution: Methods and Results. In Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023. IEEE Computer Society. 2023. p. 1922-1960. (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). doi: 10.1109/CVPRW59228.2023.00189

NTIRE 2023 Challenge on Efficient Super-Resolution: Methods and Results

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this