NTIRE 2025 Challenge on Single Image Reflection Removal in the Wild: Datasets, Methods and Results

Yang, Kangning; Cai, Jie; Ouyang, Ling; Vasluianu, Florin-Alexandru; Timofte, Radu; Ding, Jiaming; Sun, Huiming; Fu, Lan; Li, Jinlong; Ho, Chiu Man; Meng, Zibo; Li, Mingjia; Wang, Hainuo; Hu, Qiming; Wang, Jiarui; Zhao, Hao; Hu, Jin; Guo, Xiaojie; Yang, Mengru; He, Jing; Wang, Yiqing; Chen, Zhiyang; Fang, Hao; Zhang, Wei; Cong, Runmin; Hegde, Dheeraj Damodhar; Kalal, Jatin; Akalwadi, Nikhil; Tabib, Ramesh Ashok; Mudenagudi, Uma; Lin, Yu-Fan; Lee, Chia-Ming; Hsu, Chih-Chung; Zhang, Mengxin; Nathan, Sabari; Uma, K; Sasithradevi, A; Bama, B Sathya; Roomi, S. Mohamed Mansoor; Benjdira, Bilel; Ali, Anas M.; Boulila, Wadii; Dong, Wei; Li, Yunzhe; Hussein, Ali; Zhou, Han; Chen, Jun; Xiao, Zeyu; Li, Zhuoyuan

Kangning Yang, Jie Cai, Ling Ouyang, Florin-Alexandru Vasluianu, Radu Timofte, Jiaming Ding, Huiming Sun, Lan Fu, Jinlong Li, Chiu Man Ho, Zibo Meng, Mingjia Li, Hainuo Wang, Qiming Hu, Jiarui Wang, Hao Zhao, Jin Hu, Xiaojie Guo, Mengru Yang, Jing He, Yiqing Wang, Zhiyang Chen, Hao Fang, Wei Zhang, Runmin Cong, Dheeraj Damodhar Hegde, Jatin Kalal, Nikhil Akalwadi, Ramesh Ashok Tabib, Uma Mudenagudi, Yu-Fan Lin, Chia-Ming Lee, Chih-Chung Hsu, Mengxin Zhang, Sabari Nathan, K Uma, A Sasithradevi, B Sathya Bama, S. Mohamed Mansoor Roomi, Bilel Benjdira, Anas M. Ali, Wadii Boulila, Wei Dong, Yunzhe Li, Ali Hussein, Han Zhou, Jun Chen, Zeyu Xiao, Zhuoyuan Li; Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops, 2025, pp. 1301-1311

Abstract

In this paper, we review the NTIRE 2025 challenge on single-image reflection removal (SIRR) in the wild. SIRR is a fundamental task in image restoration. Despite progress in academic research, most methods are tested on synthetic images or limited real-world images, creating a gap in real-world applications. In this challenge, participants are required to process real-world images that cover a range of reflection scenarios and intensities, with the goal of generating clean images without reflections. The challenge attracted more than 200 registrations, with 11 of them participating in the final testing phase. The top-ranked methods advanced the state-of-the-art reflection removal performance and earned unanimous recognition from the five experts in the field. The proposed datasets are available at https://huggingface.co/datasets/qiuzhangTiTi/NTIRE2025-SIRR and the homepage of this challenge is at https://github.com/caijie0620/Reflection-Removal-in-the-Wild.

Related Material

[pdf] [supp]

[bibtex]

@InProceedings{Yang_2025_CVPR, author = {Yang, Kangning and Cai, Jie and Ouyang, Ling and Vasluianu, Florin-Alexandru and Timofte, Radu and Ding, Jiaming and Sun, Huiming and Fu, Lan and Li, Jinlong and Ho, Chiu Man and Meng, Zibo and Li, Mingjia and Wang, Hainuo and Hu, Qiming and Wang, Jiarui and Zhao, Hao and Hu, Jin and Guo, Xiaojie and Yang, Mengru and He, Jing and Wang, Yiqing and Chen, Zhiyang and Fang, Hao and Zhang, Wei and Cong, Runmin and Hegde, Dheeraj Damodhar and Kalal, Jatin and Akalwadi, Nikhil and Tabib, Ramesh Ashok and Mudenagudi, Uma and Lin, Yu-Fan and Lee, Chia-Ming and Hsu, Chih-Chung and Zhang, Mengxin and Nathan, Sabari and Uma, K and Sasithradevi, A and Bama, B Sathya and Roomi, S. Mohamed Mansoor and Benjdira, Bilel and Ali, Anas M. and Boulila, Wadii and Dong, Wei and Li, Yunzhe and Hussein, Ali and Zhou, Han and Chen, Jun and Xiao, Zeyu and Li, Zhuoyuan}, title = {NTIRE 2025 Challenge on Single Image Reflection Removal in the Wild: Datasets, Methods and Results}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) Workshops}, month = {June}, year = {2025}, pages = {1301-1311} }