Buchumschlag

NTIRE 2025 Challenge on Image Super-Resolution ($\times$4): Methods and Results

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Chen, Zheng, Liu, Kai, Gong, Jue, Wang, Jingkai, Sun, Lei, Wu, Zongwei, Timofte, Radu, Zhang, Yulun, Kong, Xiangyu, Yu, Xiaoxuan, Park, Hyunhee, Han, Suejin, Jeon, Hakjae, Zhang, Dafeng, Chun, Hyung-Ju, Ryou, Donghun, Ha, Inju, Han, Bohyung, Zhao, Lu, Zhang, Yuyi, Yan, Pengyu, Hu, Jiawei, Liu, Pengwei, Guo, Fengjun, Yu, Hongyuan, Xu, Pufan, Huang, Zhijuan, Cui, Shuyuan, Guo, Peng, Liu, Jiahui, Zhang, Dongkai, Zhang, Heng, Fu, Huiyuan, Ma, Huadong, Guo, Yanhui, Tian, Sisi, Liu, Xin, Liang, Jinwen, Liu, Jie, Tang, Jie, Wu, Gangshan, Xiao, Zeyu, Li, Zhuoyuan, Zhang, Yinxiang, Cai, Wenxuan, Aralikatti, Vijayalaxmi Ashok, Akalwadi, Nikhil, Rao, G Gyaneshwar, Desai, Chaitra, Tabib, Ramesh Ashok, Mudenagudi, Uma, Conde, Marcos V., Merino, Alejandro, Longarela, Bruno, Abad, Javier, Yuan, Weijun, Li, Zhan, Chen, Zhanglu, Yao, Boyang, Jain, Aagam, Singh, Milan Kumar, Kumar, Ankit, Kawa, Shubh, Singh, Divyavardhan, Sarvaiya, Anjali, Upla, Kishor, Ramachandra, Raghavendra, Lee, Chia-Ming, Lin, Yu-Fan, Hsu, Chih-Chung, Hiremath, Risheek V, Palani, Yashaswini, Jiang, Yuxuan, Zhu, Qiang, Teng, Siyue, Zhang, Fan, Zhu, Shuyuan, Zeng, Bing, Bull, David, Liao, Jingwei, Yang, Yuqing, Shao, Wenda, Zhao, Junyi, Xu, Qisheng, Xu, Kele, Khowaja, Sunder Ali, Lee, Ik Hyun, Tomar, Snehal Singh, Ray, Rajarshi, Mueller, Klaus, Chaudhary, Sachin, Vashisth, Surya, Dudhane, Akshay, Hambarde, Praful, Tazi, Satya Naryan, Patil, Prashant, Vipparthi, Santosh Kumar, Murala, Subrahmanyam, Benjdira, Bilel, Ali, Anas M., Boulila, Wadii, Moammeri, Zahra, Mahmoudi-Aznaveh, Ahmad, Karbasi, Ali, Motamednia, Hossein, Li, Liangyan, Zhao, Guanhua, Le, Kevin, Ning, Yimo, Huang, Haoxuan, Chen, Jun
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Computer Vision and Pattern Recognition
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

_version_	1866908342259023872
author	Chen, Zheng Liu, Kai Gong, Jue Wang, Jingkai Sun, Lei Wu, Zongwei Timofte, Radu Zhang, Yulun Kong, Xiangyu Yu, Xiaoxuan Park, Hyunhee Han, Suejin Jeon, Hakjae Zhang, Dafeng Chun, Hyung-Ju Ryou, Donghun Ha, Inju Han, Bohyung Zhao, Lu Zhang, Yuyi Yan, Pengyu Hu, Jiawei Liu, Pengwei Guo, Fengjun Yu, Hongyuan Xu, Pufan Huang, Zhijuan Cui, Shuyuan Guo, Peng Liu, Jiahui Zhang, Dongkai Zhang, Heng Fu, Huiyuan Ma, Huadong Guo, Yanhui Tian, Sisi Liu, Xin Liang, Jinwen Liu, Jie Tang, Jie Wu, Gangshan Xiao, Zeyu Li, Zhuoyuan Zhang, Yinxiang Cai, Wenxuan Aralikatti, Vijayalaxmi Ashok Akalwadi, Nikhil Rao, G Gyaneshwar Desai, Chaitra Tabib, Ramesh Ashok Mudenagudi, Uma Conde, Marcos V. Merino, Alejandro Longarela, Bruno Abad, Javier Yuan, Weijun Li, Zhan Chen, Zhanglu Yao, Boyang Jain, Aagam Singh, Milan Kumar Kumar, Ankit Kawa, Shubh Singh, Divyavardhan Sarvaiya, Anjali Upla, Kishor Ramachandra, Raghavendra Lee, Chia-Ming Lin, Yu-Fan Hsu, Chih-Chung Hiremath, Risheek V Palani, Yashaswini Jiang, Yuxuan Zhu, Qiang Teng, Siyue Zhang, Fan Zhu, Shuyuan Zeng, Bing Bull, David Liao, Jingwei Yang, Yuqing Shao, Wenda Zhao, Junyi Xu, Qisheng Xu, Kele Khowaja, Sunder Ali Lee, Ik Hyun Tomar, Snehal Singh Ray, Rajarshi Mueller, Klaus Chaudhary, Sachin Vashisth, Surya Dudhane, Akshay Hambarde, Praful Tazi, Satya Naryan Patil, Prashant Vipparthi, Santosh Kumar Murala, Subrahmanyam Benjdira, Bilel Ali, Anas M. Boulila, Wadii Moammeri, Zahra Mahmoudi-Aznaveh, Ahmad Karbasi, Ali Motamednia, Hossein Li, Liangyan Zhao, Guanhua Le, Kevin Ning, Yimo Huang, Haoxuan Chen, Jun
author_facet	Chen, Zheng Liu, Kai Gong, Jue Wang, Jingkai Sun, Lei Wu, Zongwei Timofte, Radu Zhang, Yulun Kong, Xiangyu Yu, Xiaoxuan Park, Hyunhee Han, Suejin Jeon, Hakjae Zhang, Dafeng Chun, Hyung-Ju Ryou, Donghun Ha, Inju Han, Bohyung Zhao, Lu Zhang, Yuyi Yan, Pengyu Hu, Jiawei Liu, Pengwei Guo, Fengjun Yu, Hongyuan Xu, Pufan Huang, Zhijuan Cui, Shuyuan Guo, Peng Liu, Jiahui Zhang, Dongkai Zhang, Heng Fu, Huiyuan Ma, Huadong Guo, Yanhui Tian, Sisi Liu, Xin Liang, Jinwen Liu, Jie Tang, Jie Wu, Gangshan Xiao, Zeyu Li, Zhuoyuan Zhang, Yinxiang Cai, Wenxuan Aralikatti, Vijayalaxmi Ashok Akalwadi, Nikhil Rao, G Gyaneshwar Desai, Chaitra Tabib, Ramesh Ashok Mudenagudi, Uma Conde, Marcos V. Merino, Alejandro Longarela, Bruno Abad, Javier Yuan, Weijun Li, Zhan Chen, Zhanglu Yao, Boyang Jain, Aagam Singh, Milan Kumar Kumar, Ankit Kawa, Shubh Singh, Divyavardhan Sarvaiya, Anjali Upla, Kishor Ramachandra, Raghavendra Lee, Chia-Ming Lin, Yu-Fan Hsu, Chih-Chung Hiremath, Risheek V Palani, Yashaswini Jiang, Yuxuan Zhu, Qiang Teng, Siyue Zhang, Fan Zhu, Shuyuan Zeng, Bing Bull, David Liao, Jingwei Yang, Yuqing Shao, Wenda Zhao, Junyi Xu, Qisheng Xu, Kele Khowaja, Sunder Ali Lee, Ik Hyun Tomar, Snehal Singh Ray, Rajarshi Mueller, Klaus Chaudhary, Sachin Vashisth, Surya Dudhane, Akshay Hambarde, Praful Tazi, Satya Naryan Patil, Prashant Vipparthi, Santosh Kumar Murala, Subrahmanyam Benjdira, Bilel Ali, Anas M. Boulila, Wadii Moammeri, Zahra Mahmoudi-Aznaveh, Ahmad Karbasi, Ali Motamednia, Hossein Li, Liangyan Zhao, Guanhua Le, Kevin Ning, Yimo Huang, Haoxuan Chen, Jun
contents	This paper presents the NTIRE 2025 image super-resolution ($\times$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 $\times$4 scaling factor. The objective is to develop effective network designs or solutions that achieve state-of-the-art SR performance. To reflect the dual objectives of image SR research, the challenge includes two sub-tracks: (1) a restoration track, emphasizes pixel-wise accuracy and ranks submissions based on PSNR; (2) a perceptual track, focuses on visual realism and ranks results by a perceptual score. A total of 286 participants registered for the competition, with 25 teams submitting valid entries. This report summarizes the challenge design, datasets, evaluation protocol, the main results, and methods of each team. The challenge serves as a benchmark to advance the state of the art and foster progress in image SR.
format	Preprint
id	arxiv_https___arxiv_org_abs_2504_14582
institution	arXiv
publishDate	2025
record_format	arxiv
spellingShingle	NTIRE 2025 Challenge on Image Super-Resolution ($\times$4): Methods and Results Chen, Zheng Liu, Kai Gong, Jue Wang, Jingkai Sun, Lei Wu, Zongwei Timofte, Radu Zhang, Yulun Kong, Xiangyu Yu, Xiaoxuan Park, Hyunhee Han, Suejin Jeon, Hakjae Zhang, Dafeng Chun, Hyung-Ju Ryou, Donghun Ha, Inju Han, Bohyung Zhao, Lu Zhang, Yuyi Yan, Pengyu Hu, Jiawei Liu, Pengwei Guo, Fengjun Yu, Hongyuan Xu, Pufan Huang, Zhijuan Cui, Shuyuan Guo, Peng Liu, Jiahui Zhang, Dongkai Zhang, Heng Fu, Huiyuan Ma, Huadong Guo, Yanhui Tian, Sisi Liu, Xin Liang, Jinwen Liu, Jie Tang, Jie Wu, Gangshan Xiao, Zeyu Li, Zhuoyuan Zhang, Yinxiang Cai, Wenxuan Aralikatti, Vijayalaxmi Ashok Akalwadi, Nikhil Rao, G Gyaneshwar Desai, Chaitra Tabib, Ramesh Ashok Mudenagudi, Uma Conde, Marcos V. Merino, Alejandro Longarela, Bruno Abad, Javier Yuan, Weijun Li, Zhan Chen, Zhanglu Yao, Boyang Jain, Aagam Singh, Milan Kumar Kumar, Ankit Kawa, Shubh Singh, Divyavardhan Sarvaiya, Anjali Upla, Kishor Ramachandra, Raghavendra Lee, Chia-Ming Lin, Yu-Fan Hsu, Chih-Chung Hiremath, Risheek V Palani, Yashaswini Jiang, Yuxuan Zhu, Qiang Teng, Siyue Zhang, Fan Zhu, Shuyuan Zeng, Bing Bull, David Liao, Jingwei Yang, Yuqing Shao, Wenda Zhao, Junyi Xu, Qisheng Xu, Kele Khowaja, Sunder Ali Lee, Ik Hyun Tomar, Snehal Singh Ray, Rajarshi Mueller, Klaus Chaudhary, Sachin Vashisth, Surya Dudhane, Akshay Hambarde, Praful Tazi, Satya Naryan Patil, Prashant Vipparthi, Santosh Kumar Murala, Subrahmanyam Benjdira, Bilel Ali, Anas M. Boulila, Wadii Moammeri, Zahra Mahmoudi-Aznaveh, Ahmad Karbasi, Ali Motamednia, Hossein Li, Liangyan Zhao, Guanhua Le, Kevin Ning, Yimo Huang, Haoxuan Chen, Jun Computer Vision and Pattern Recognition This paper presents the NTIRE 2025 image super-resolution ($\times$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 $\times$4 scaling factor. The objective is to develop effective network designs or solutions that achieve state-of-the-art SR performance. To reflect the dual objectives of image SR research, the challenge includes two sub-tracks: (1) a restoration track, emphasizes pixel-wise accuracy and ranks submissions based on PSNR; (2) a perceptual track, focuses on visual realism and ranks results by a perceptual score. A total of 286 participants registered for the competition, with 25 teams submitting valid entries. This report summarizes the challenge design, datasets, evaluation protocol, the main results, and methods of each team. The challenge serves as a benchmark to advance the state of the art and foster progress in image SR.
title	NTIRE 2025 Challenge on Image Super-Resolution ($\times$4): Methods and Results
topic	Computer Vision and Pattern Recognition
url	https://arxiv.org/abs/2504.14582