2nd place in the NTIRE 2025 Low Light Image Enhancement Challenge
Created on April 02, 2025
2025 · challenge low-light
Our team, Imagine, finished 2nd overall in the NTIRE 2025 Low Light Image Enhancement Challenge and achieved the highest PSNR on the test set (26.35 dB). The challenge drew 762 registered participants; the methods and final rankings are described in the challenge report (Liu et al., 2025).
Our team (Imagine) ranked 2nd overall and 1st in PSNR.
This paper presents a comprehensive review of the NTIRE 2025 Low-Light Image Enhancement (LLIE) Challenge, highlighting the proposed solutions and final outcomes. The objective of the challenge is to identify effective networks capable of producing brighter, clearer, and visually compelling images under diverse and challenging conditions. A remarkable total of 762 participants registered for the competition, with 28 teams ultimately submitting valid entries. This paper thoroughly evaluates the state-of-the-art advancements in LLIE, showcasing the significant progress.
@inproceedings{liu2025ntire,title={{NTIRE} 2025 Challenge on Low Light Image Enhancement: Methods and Results},author={Liu, Xiaoning and Wu, Zongwei and Vasluianu, Florin-Alexandru and Yan, Hailong and Ren, Bin and Zhang, Yulun and Gu, Shuhang and Zhang, Le and Zhu, Ce and Timofte, Radu and Shi, Kangbiao and Feng, Yixu and Hu, Tao and Cao, Yu and Wu, Peng and Liang, Yijin and Zhang, Yanning and Yan, Qingsen and Zhou, Han and Dong, Wei and Min, Yan and Kishawy, Mohab and Chen, Jun and Yu, Pengpeng and Park, Anjin and Lee, Seung-Soo and Park, Young-Joon and Hu, Zixiao and Liu, Junyv and Zhang, Huilin and Zhang, Jun and Wan, Fei and Xu, Bingxin and Liu, Hongzhe and Xu, Cheng and Pan, Weiguo and Dai, Songyin and Yi, Xunpeng and Yan, Qinglong and Zhang, Yibing and Ma, Jiayi and Hu, Changhui and Hu, Kerui and Jing, Donghang and Chen, Tiesheng and Jin, Zhi and Wu, Hongjun and Huang, Biao and Ling, Haitao and Wu, Jiahao and Zhan, Dandan and Rao, G Gyaneshwar and Aralikatti, Vijayalaxmi Ashok and Akalwadi, Nikhil and Tabib, Ramesh Ashok and Mudenagudi, Uma and Lin, Ruirui and Huang, Guoxi and Anantrasirichai, Nantheera and Yang, Qirui and Brateanu, Alexandru and Orhei, Ciprian and Ancuti, Cosmin and Feijoo, Daniel and Benito, Juan C. and Garcia, Alvaro and Conde, Marcos V. and Qin, Yang and Balmez, Raul and Ali, Anas M. and Benjdira, Bilel and Boulila, Wadii and Mao, Tianyi and Zheng, Huan and Wei, Yanyan and Tang, Shengeng and Guo, Dan and Zhang, Zhao and Nathan, Sabari and Uma, K and Sasithradevi, A and Bama, B Sathya and Roomi, S. Mohamed Mansoor and Li, Ao and Zhang, Xiangtao and Liu, Zhe and Tang, Yijie and Tang, Jialong and Fu, Zhicheng and Chen, Gong and Nasti, Joe and Nicholson, John and Xiao, Zeyu and Li, Zhuoyuan and Kulkarni, Ashutosh and Patil, Prashant W. and Vipparthi, Santosh Kumar and Murala, Subrahmanyam and Liu, Duan and Li, Weile and Lu, Hangyuan and Liu, Rixian and Wang, Tengfeng and Liang, Jinxing and Yu, Chenxin},booktitle={Proceedings of the {IEEE/CVF} Conference on Computer Vision and Pattern Recognition ({CVPR}) Workshops},month=jun,year={2025},pages={1196--1206},doi={10.1109/CVPRW67362.2025.00114},}