NTIRE 2025 Challenge on Image Super-Resolution (× 4): Methods and Results

Zheng Chen; Kai Liu; Jue Gong; Jingkai Wang; Lei Sun; Zongwei Wu; Radu Timofte; Yulun Zhang; Xiangyu Kong; Xiaoxuan Yu; Hyunhee Park; Suejin Han; Hakjae Jeon; Dafeng Zhang; Hyung Ju Chun; Donghun Ryou; Inju Ha; Bohyung Han; Lu Zhao; Yuyi Zhang; Pengyu Yan; Jiawei Hu; Pengwei Liu; Fengjun Guo; Hongyuan Yu; Pufan Xu; Zhijuan Huang; Shuyuan Cui; Peng Guo; Jiahui Liu; Dongkai Zhang; Heng Zhang; Huiyuan Fu; Huadong Ma; Yanhui Guo; Sisi Tian; Xin Liu; Jinwen Liang; Jie Liu; Jie Tang; Gangshan Wu; Zeyu Xiao; Zhuoyuan Li; Yinxiang Zhang; Wenxuan Cai; Vijayalaxmi Ashok Aralikatti; Nikhil Akalwadi; G. Gyaneshwar Rao; Chaitra Desai; Ramesh Ashok Tabib; Uma Mudenagudi; Marcos V. Conde; Alejandro Merino; Bruno Longarela; Javier Abad; Weijun Yuan; Zhan Li; Zhanglu Chen; Boyang Yao; Aagam Jain; Milan Kumar Singh; Ankit Kumar; Shubh Kawa; Divyavardhan Singh; Anjali Sarvaiya; Kishor Upla; Raghavendra Ramachandra; Chia Ming Lee; Yu Fan Lin; Chih Chung Hsu; Risheek V. Hiremath; Yashaswini Palani; Yuxuan Jiang; Qiang Zhu; Siyue Teng; Fan Zhang; Shuyuan Zhu; Bing Zeng; David Bull; Jingwei Liao; Yuqing Yang; Wenda Shao; Junyi Zhao; Qisheng Xu; Kele Xu; Sunder Ali Khowaja; Ik Hyun Lee; Snehal Singh Tomar; Rajarshi Ray; Klaus Mueller; Sachin Chaudhary; Surya Vashisth; Akshay Dudhane; Praful Hambarde; Satya Naryan Tazi; Prashant Patil; Santosh Kumar Vipparthi; Subrahmanyam Murala; Bilel Benjdira; Anas M. Ali; Wadii Boulila; Zahra Moammeri; Ahmad Mahmoudi-Aznaveh; Ali Karbasi; Hossein Motamednia; Liangyan Li; Guanhua Zhao; Kevin Le; Yimo Ning; Haoxuan Huang; Jun Chen

doi:10.1109/CVPRW67362.2025.00141

NTIRE 2025 Challenge on Image Super-Resolution (× 4): Methods and Results

Zheng Chen
, Kai Liu
, Jue Gong
, Jingkai Wang
, Lei Sun
, Zongwei Wu
, Radu Timofte
, Yulun Zhang
, Xiangyu Kong
, Xiaoxuan Yu
, Hyunhee Park
, Suejin Han
, Hakjae Jeon
, Dafeng Zhang
, Hyung Ju Chun
, Donghun Ryou
, Inju Ha
, Bohyung Han
, Lu Zhao
, Yuyi Zhang

Pengyu Yan, Jiawei Hu, Pengwei Liu, Fengjun Guo, Hongyuan Yu, Pufan Xu, Zhijuan Huang, Shuyuan Cui, Peng Guo, Jiahui Liu, Dongkai Zhang, Heng Zhang, Huiyuan Fu, Huadong Ma, Yanhui Guo, Sisi Tian, Xin Liu, Jinwen Liang, Jie Liu, Jie Tang, Gangshan Wu, Zeyu Xiao, Zhuoyuan Li, Yinxiang Zhang, Wenxuan Cai, Vijayalaxmi Ashok Aralikatti, Nikhil Akalwadi, G. Gyaneshwar Rao, Chaitra Desai, Ramesh Ashok Tabib, Uma Mudenagudi, Marcos V. Conde, Alejandro Merino, Bruno Longarela, Javier Abad, Weijun Yuan, Zhan Li, Zhanglu Chen, Boyang Yao, Aagam Jain, Milan Kumar Singh, Ankit Kumar, Shubh Kawa, Divyavardhan Singh, Anjali Sarvaiya, Kishor Upla, Raghavendra Ramachandra, Chia Ming Lee, Yu Fan Lin, Chih Chung Hsu, Risheek V. Hiremath, Yashaswini Palani, Yuxuan Jiang, Qiang Zhu, Siyue Teng, Fan Zhang, Shuyuan Zhu, Bing Zeng, David Bull, Jingwei Liao, Yuqing Yang, Wenda Shao, Junyi Zhao, Qisheng Xu, Kele Xu, Sunder Ali Khowaja, Ik Hyun Lee, Snehal Singh Tomar, Rajarshi Ray, Klaus Mueller, Sachin Chaudhary, Surya Vashisth, Akshay Dudhane, Praful Hambarde, Satya Naryan Tazi, Prashant Patil, Santosh Kumar Vipparthi, Subrahmanyam Murala, Bilel Benjdira, Anas M. Ali, Wadii Boulila, Zahra Moammeri, Ahmad Mahmoudi-Aznaveh, Ali Karbasi, Hossein Motamednia, Liangyan Li, Guanhua Zhao, Kevin Le, Yimo Ning, Haoxuan Huang, Jun Chen

School of Computer Science

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

Abstract

This paper presents the NTIRE 2025 image super-resolution (× 4) challenge, one of the associated competitions of the 10th NTIRE Workshop at CVPR 2025. The challenge aims to recover high-resolution (HR) images from low-resolution (LR) counterparts generated through bicubic downsampling with a × 4 scaling factor. The objective is to develop effective network designs or solutions that achieve state-of-the-art SR performance. To reflect the dual objectives of image SR research, the challenge includes two sub-tracks: (1) a restoration track, emphasizes pixel-wise accuracy and ranks submissions based on PSNR; (2) a perceptual track, focuses on visual realism and ranks results by a perceptual score. A total of 286 participants registered for the competition, with 25 teams submitting valid entries. This report summarizes the challenge design, datasets, evaluation protocol, the main results, and methods of each team. The challenge serves as a benchmark to advance the state of the art and foster progress in image SR.

Original language	English
Title of host publication	Proceedings - 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025
Publisher	IEEE Computer Society
Pages	1516-1526
Number of pages	11
ISBN (Electronic)	9798331599942
DOIs	https://doi.org/10.1109/CVPRW67362.2025.00141
Publication status	Published - 2025
Event	2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025 - Nashville, United States Duration: 11 Jun 2025 → 12 Jun 2025

Publication series

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

Conference

Conference	2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025
Country/Territory	United States
City	Nashville
Period	11/06/25 → 12/06/25

Access to Document

10.1109/CVPRW67362.2025.00141

Cite this

Chen, Z., Liu, K., Gong, J., Wang, J., Sun, L., Wu, Z., Timofte, R., Zhang, Y., Kong, X., Yu, X., Park, H., Han, S., Jeon, H., Zhang, D., Chun, H. J., Ryou, D., Ha, I., Han, B., Zhao, L., ... Chen, J. (2025). NTIRE 2025 Challenge on Image Super-Resolution (× 4): Methods and Results. In Proceedings - 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025 (pp. 1516-1526). (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). IEEE Computer Society. https://doi.org/10.1109/CVPRW67362.2025.00141

@inproceedings{4033bc6951774a549d6b524ae782cc55,

title = "NTIRE 2025 Challenge on Image Super-Resolution (× 4): Methods and Results",

abstract = "This paper presents the NTIRE 2025 image super-resolution (× 4) challenge, one of the associated competitions of the 10th NTIRE Workshop at CVPR 2025. The challenge aims to recover high-resolution (HR) images from low-resolution (LR) counterparts generated through bicubic downsampling with a × 4 scaling factor. The objective is to develop effective network designs or solutions that achieve state-of-the-art SR performance. To reflect the dual objectives of image SR research, the challenge includes two sub-tracks: (1) a restoration track, emphasizes pixel-wise accuracy and ranks submissions based on PSNR; (2) a perceptual track, focuses on visual realism and ranks results by a perceptual score. A total of 286 participants registered for the competition, with 25 teams submitting valid entries. This report summarizes the challenge design, datasets, evaluation protocol, the main results, and methods of each team. The challenge serves as a benchmark to advance the state of the art and foster progress in image SR.",

author = "Zheng Chen and Kai Liu and Jue Gong and Jingkai Wang and Lei Sun and Zongwei Wu and Radu Timofte and Yulun Zhang and Xiangyu Kong and Xiaoxuan Yu and Hyunhee Park and Suejin Han and Hakjae Jeon and Dafeng Zhang and Chun, \{Hyung Ju\} and Donghun Ryou and Inju Ha and Bohyung Han and Lu Zhao and Yuyi Zhang and Pengyu Yan and Jiawei Hu and Pengwei Liu and Fengjun Guo and Hongyuan Yu and Pufan Xu and Zhijuan Huang and Shuyuan Cui and Peng Guo and Jiahui Liu and Dongkai Zhang and Heng Zhang and Huiyuan Fu and Huadong Ma and Yanhui Guo and Sisi Tian and Xin Liu and Jinwen Liang and Jie Liu and Jie Tang and Gangshan Wu and Zeyu Xiao and Zhuoyuan Li and Yinxiang Zhang and Wenxuan Cai and Aralikatti, \{Vijayalaxmi Ashok\} and Nikhil Akalwadi and Rao, \{G. Gyaneshwar\} and Chaitra Desai and Tabib, \{Ramesh Ashok\} and Uma Mudenagudi and Conde, \{Marcos V.\} and Alejandro Merino and Bruno Longarela and Javier Abad and Weijun Yuan and Zhan Li and Zhanglu Chen and Boyang Yao and Aagam Jain and Singh, \{Milan Kumar\} and Ankit Kumar and Shubh Kawa and Divyavardhan Singh and Anjali Sarvaiya and Kishor Upla and Raghavendra Ramachandra and Lee, \{Chia Ming\} and Lin, \{Yu Fan\} and Hsu, \{Chih Chung\} and Hiremath, \{Risheek V.\} and Yashaswini Palani and Yuxuan Jiang and Qiang Zhu and Siyue Teng and Fan Zhang and Shuyuan Zhu and Bing Zeng and David Bull and Jingwei Liao and Yuqing Yang and Wenda Shao and Junyi Zhao and Qisheng Xu and Kele Xu and Khowaja, \{Sunder Ali\} and Lee, \{Ik Hyun\} and Tomar, \{Snehal Singh\} and Rajarshi Ray and Klaus Mueller and Sachin Chaudhary and Surya Vashisth and Akshay Dudhane and Praful Hambarde and Tazi, \{Satya Naryan\} and Prashant Patil and Vipparthi, \{Santosh Kumar\} and Subrahmanyam Murala and Bilel Benjdira and Ali, \{Anas M.\} and Wadii Boulila and Zahra Moammeri and Ahmad Mahmoudi-Aznaveh and Ali Karbasi and Hossein Motamednia and Liangyan Li and Guanhua Zhao and Kevin Le and Yimo Ning and Haoxuan Huang and Jun Chen",

note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025 ; Conference date: 11-06-2025 Through 12-06-2025",

year = "2025",

doi = "10.1109/CVPRW67362.2025.00141",

language = "English",

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

publisher = "IEEE Computer Society",

pages = "1516--1526",

booktitle = "Proceedings - 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025",

address = "United States",

}

Chen, Z, Liu, K, Gong, J, Wang, J, Sun, L, Wu, Z, Timofte, R, Zhang, Y, Kong, X, Yu, X, Park, H, Han, S, Jeon, H, Zhang, D, Chun, HJ, Ryou, D, Ha, I, Han, B, Zhao, L, Zhang, Y, Yan, P, Hu, J, Liu, P, Guo, F, Yu, H, Xu, P, Huang, Z, Cui, S, Guo, P, Liu, J, Zhang, D, Zhang, H, Fu, H, Ma, H, Guo, Y, Tian, S, Liu, X, Liang, J, Liu, J, Tang, J, Wu, G, Xiao, Z, Li, Z, Zhang, Y, Cai, W, Aralikatti, VA, Akalwadi, N, Rao, GG, Desai, C, Tabib, RA, Mudenagudi, U, Conde, MV, Merino, A, Longarela, B, Abad, J, Yuan, W, Li, Z, Chen, Z, Yao, B, Jain, A, Singh, MK, Kumar, A, Kawa, S, Singh, D, Sarvaiya, A, Upla, K, Ramachandra, R, Lee, CM, Lin, YF, Hsu, CC, Hiremath, RV, Palani, Y, Jiang, Y, Zhu, Q, Teng, S, Zhang, F, Zhu, S, Zeng, B, Bull, D, Liao, J, Yang, Y, Shao, W, Zhao, J, Xu, Q, Xu, K, Khowaja, SA, Lee, IH, Tomar, SS, Ray, R, Mueller, K, Chaudhary, S, Vashisth, S, Dudhane, A, Hambarde, P, Tazi, SN, Patil, P, Vipparthi, SK, Murala, S, Benjdira, B, Ali, AM, Boulila, W, Moammeri, Z, Mahmoudi-Aznaveh, A, Karbasi, A, Motamednia, H, Li, L, Zhao, G, Le, K, Ning, Y, Huang, H & Chen, J 2025, NTIRE 2025 Challenge on Image Super-Resolution (× 4): Methods and Results. in Proceedings - 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, IEEE Computer Society, pp. 1516-1526, 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025, Nashville, United States, 11/06/25. https://doi.org/10.1109/CVPRW67362.2025.00141

NTIRE 2025 Challenge on Image Super-Resolution (× 4): Methods and Results. / Chen, Zheng; Liu, Kai; Gong, Jue et al.
Proceedings - 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025. IEEE Computer Society, 2025. p. 1516-1526 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops).

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

TY - GEN

T1 - NTIRE 2025 Challenge on Image Super-Resolution (× 4)

T2 - 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025

AU - Chen, Zheng

AU - Liu, Kai

AU - Gong, Jue

AU - Wang, Jingkai

AU - Sun, Lei

AU - Wu, Zongwei

AU - Timofte, Radu

AU - Zhang, Yulun

AU - Kong, Xiangyu

AU - Yu, Xiaoxuan

AU - Park, Hyunhee

AU - Han, Suejin

AU - Jeon, Hakjae

AU - Zhang, Dafeng

AU - Chun, Hyung Ju

AU - Ryou, Donghun

AU - Ha, Inju

AU - Han, Bohyung

AU - Zhao, Lu

AU - Zhang, Yuyi

AU - Yan, Pengyu

AU - Hu, Jiawei

AU - Liu, Pengwei

AU - Guo, Fengjun

AU - Yu, Hongyuan

AU - Xu, Pufan

AU - Huang, Zhijuan

AU - Cui, Shuyuan

AU - Guo, Peng

AU - Liu, Jiahui

AU - Zhang, Dongkai

AU - Zhang, Heng

AU - Fu, Huiyuan

AU - Ma, Huadong

AU - Guo, Yanhui

AU - Tian, Sisi

AU - Liu, Xin

AU - Liang, Jinwen

AU - Liu, Jie

AU - Tang, Jie

AU - Wu, Gangshan

AU - Xiao, Zeyu

AU - Li, Zhuoyuan

AU - Zhang, Yinxiang

AU - Cai, Wenxuan

AU - Aralikatti, Vijayalaxmi Ashok

AU - Akalwadi, Nikhil

AU - Rao, G. Gyaneshwar

AU - Desai, Chaitra

AU - Tabib, Ramesh Ashok

AU - Mudenagudi, Uma

AU - Conde, Marcos V.

AU - Merino, Alejandro

AU - Longarela, Bruno

AU - Abad, Javier

AU - Yuan, Weijun

AU - Li, Zhan

AU - Chen, Zhanglu

AU - Yao, Boyang

AU - Jain, Aagam

AU - Singh, Milan Kumar

AU - Kumar, Ankit

AU - Kawa, Shubh

AU - Singh, Divyavardhan

AU - Sarvaiya, Anjali

AU - Upla, Kishor

AU - Ramachandra, Raghavendra

AU - Lee, Chia Ming

AU - Lin, Yu Fan

AU - Hsu, Chih Chung

AU - Hiremath, Risheek V.

AU - Palani, Yashaswini

AU - Jiang, Yuxuan

AU - Zhu, Qiang

AU - Teng, Siyue

AU - Zhang, Fan

AU - Zhu, Shuyuan

AU - Zeng, Bing

AU - Bull, David

AU - Liao, Jingwei

AU - Yang, Yuqing

AU - Shao, Wenda

AU - Zhao, Junyi

AU - Xu, Qisheng

AU - Xu, Kele

AU - Khowaja, Sunder Ali

AU - Lee, Ik Hyun

AU - Tomar, Snehal Singh

AU - Ray, Rajarshi

AU - Mueller, Klaus

AU - Chaudhary, Sachin

AU - Vashisth, Surya

AU - Dudhane, Akshay

AU - Hambarde, Praful

AU - Tazi, Satya Naryan

AU - Patil, Prashant

AU - Vipparthi, Santosh Kumar

AU - Murala, Subrahmanyam

AU - Benjdira, Bilel

AU - Ali, Anas M.

AU - Boulila, Wadii

AU - Moammeri, Zahra

AU - Mahmoudi-Aznaveh, Ahmad

AU - Karbasi, Ali

AU - Motamednia, Hossein

AU - Li, Liangyan

AU - Zhao, Guanhua

AU - Le, Kevin

AU - Ning, Yimo

AU - Huang, Haoxuan

AU - Chen, Jun

PY - 2025

Y1 - 2025

N2 - This paper presents the NTIRE 2025 image super-resolution (× 4) challenge, one of the associated competitions of the 10th NTIRE Workshop at CVPR 2025. The challenge aims to recover high-resolution (HR) images from low-resolution (LR) counterparts generated through bicubic downsampling with a × 4 scaling factor. The objective is to develop effective network designs or solutions that achieve state-of-the-art SR performance. To reflect the dual objectives of image SR research, the challenge includes two sub-tracks: (1) a restoration track, emphasizes pixel-wise accuracy and ranks submissions based on PSNR; (2) a perceptual track, focuses on visual realism and ranks results by a perceptual score. A total of 286 participants registered for the competition, with 25 teams submitting valid entries. This report summarizes the challenge design, datasets, evaluation protocol, the main results, and methods of each team. The challenge serves as a benchmark to advance the state of the art and foster progress in image SR.

AB - This paper presents the NTIRE 2025 image super-resolution (× 4) challenge, one of the associated competitions of the 10th NTIRE Workshop at CVPR 2025. The challenge aims to recover high-resolution (HR) images from low-resolution (LR) counterparts generated through bicubic downsampling with a × 4 scaling factor. The objective is to develop effective network designs or solutions that achieve state-of-the-art SR performance. To reflect the dual objectives of image SR research, the challenge includes two sub-tracks: (1) a restoration track, emphasizes pixel-wise accuracy and ranks submissions based on PSNR; (2) a perceptual track, focuses on visual realism and ranks results by a perceptual score. A total of 286 participants registered for the competition, with 25 teams submitting valid entries. This report summarizes the challenge design, datasets, evaluation protocol, the main results, and methods of each team. The challenge serves as a benchmark to advance the state of the art and foster progress in image SR.

UR - https://www.scopus.com/pages/publications/105017848752

U2 - 10.1109/CVPRW67362.2025.00141

DO - 10.1109/CVPRW67362.2025.00141

M3 - Conference contribution

AN - SCOPUS:105017848752

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

SP - 1516

EP - 1526

BT - Proceedings - 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025

PB - IEEE Computer Society

Y2 - 11 June 2025 through 12 June 2025

ER -

Chen Z, Liu K, Gong J, Wang J, Sun L, Wu Z et al. NTIRE 2025 Challenge on Image Super-Resolution (× 4): Methods and Results. In Proceedings - 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2025. IEEE Computer Society. 2025. p. 1516-1526. (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops). doi: 10.1109/CVPRW67362.2025.00141

NTIRE 2025 Challenge on Image Super-Resolution (× 4): Methods and Results

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this