-
[pdf]
[supp]
[bibtex]@InProceedings{Chen_2025_CVPR, author = {Chen, Zheng and Liu, Kai and Gong, Jue and Wang, Jingkai and Sun, Lei and Wu, Zongwei and Timofte, Radu and Zhang, Yulun and Kong, Xiangyu and Yu, Xiaoxuan and Park, Hyunhee and Han, Suejin and Jeon, Hakjae and Zhang, Dafeng and Chun, Hyung-Ju and Ryou, Donghun and Ha, Inju and Han, Bohyung and Zhao, Lu and Zhang, Yuyi and Yan, Pengyu and Hu, Jiawei and Liu, Pengwei and Guo, Fengjun and Yu, Hongyuan and Xu, Pufan and Huang, Zhijuan and Cui, Shuyuan and Guo, Peng and Liu, Jiahui and Zhang, Dongkai and Zhang, Heng and Fu, Huiyuan and Ma, Huadong and Guo, Yanhui and Tian, Sisi and Liu, Xin and Liang, Jinwen and Liu, Jie and Tang, Jie and Wu, Gangshan and Xiao, Zeyu and Li, Zhuoyuan and Zhang, Yinxiang and Cai, Wenxuan and Aralikatti, Vijayalaxmi Ashok and Akalwadi, Nikhil and Rao, G Gyaneshwar and Desai, Chaitra and Tabib, Ramesh Ashok and Mudenagudi, Uma and Conde, Marcos V. and Merino, Alejandro and Longarela, Bruno and Abad, Javier and Yuan, Weijun and Li, Zhan and Chen, Zhanglu and Yao, Boyang and Jain, Aagam and Singh, Milan Kumar and Kumar, Ankit and Kawa, Shubh and Singh, Divyavardhan and Sarvaiya, Anjali and Upla, Kishor and Ramachandra, Raghavendra and Lee, Chia Ming and Lin, Yu-Fan and Hsu, Chih-Chung and Hiremath, Risheek V and Palani, Yashaswini and Jiang, Yuxuan and Zhu, Qiang and Teng, Siyue and Zhang, Fan and Zhu, Shuyuan and Zeng, Bing and Bull, David and Liao, Jingwei and Yang, Yuqing and Shao, Wenda and Zhao, Junyi and Xu, Qisheng and Xu, Kele and Khowaja, Sunder Ali and Lee, Ik Hyun and Tomar, Snehal Singh and Ray, Rajarshi and Mueller, Klaus and Chaudhary, Sachin and Vashisth, Surya and Dudhane, Akshay and Hambarde, Praful and Tazi, Satya Naryan and Patil, Prashant and Vipparthi, Santosh Kumar and Murala, Subrahmanyam and Benjdira, Bilel and Ali, Anas M. and Boulila, Wadii and Moammeri, Zahra and Mahmoudi-Aznaveh, Ahmad and Karbasi, Ali and Motamednia, Hossein and Li, Liangyan and Zhao, Guanhua and Le, Kevin and Ning, Yimo and Huang, Haoxuan and Chen, Jun}, title = {NTIRE 2025 Challenge on Image Super-Resolution (x4): Methods and Results}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {1525-1535} }
NTIRE 2025 Challenge on Image Super-Resolution (x4): Methods and Results
Abstract
This paper presents the NTIRE 2025 image super-resolution (x4) 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 x4 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.
Related Material