I entered RetinexDualV2 in the NTIRE 2026 challenges, held with the CVPR 2026 workshops:
4th place in the Second Challenge on Day and Night Raindrop Removal for Dual-Focused Images. The challenge used the real-world Raindrop Clarity dataset; 168 teams registered and 17 submitted valid final solutions (Li et al., 2026).
5th place in Track 2, Joint Denoising and Low-Light Image Enhancement (JDLLIE), of the Low Light Image Enhancement Challenge (Ciubotariu et al., 2026).
Our team (RetinexDualV2) ranked 4th in the challenge.
This paper presents an overview of the NTIRE 2026 Second Challenge on Day and Night Raindrop Removal for Dual-Focused Images. Building upon the success of the first edition, this challenge attracted a wide range of impressive solutions, all developed and evaluated on our real-world Raindrop Clarity dataset. For this edition, we adjust the dataset with 14,139 images for training, 407 images for validation, and 593 images for testing. The primary goal of this challenge is to establish a strong and practical benchmark for the removal of raindrops under various illumination and focus conditions. In total, 168 teams have registered for the competition, and 17 teams submitted valid final solutions and fact sheets for the testing phase. The submitted methods achieved strong performance on the Raindrop Clarity dataset, demonstrating the growing progress in this challenging task. The project website is available at https://lixinustc.github.io/CVPR-NTIRE2026-RainDrop-Competition.github.io/.
@inproceedings{li2026ntire_raindrop,title={{NTIRE} 2026 The Second Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results},author={Li, Xin and Jin, Yeying and Yao, Suhang and Lin, Beibei and Fan, Zhaoxin and Yan, Wending and Jin, Xin and Wu, Zongwei and Li, Bingchen and Shi, Peishu and Wang, Yufei and Li, Yu and Chen, Zhibo and Wen, Bihan and Tan, Robby T. and Timofte, Radu and Li, Runzhe and Jiang, Kui and Yu, Zhaocheng and Chen, Yiang and Jiang, Junjun and Liu, Xianming and Gu, Hongde and Li, Zeliang and You, Mache and Dong, Jiangxin and Pan, Jinshan and Rong, Qiyu and Shao, Bowen and Jing, Hongyuan and Zhang, Mengmeng and Ding, Bo and Zhang, Hui and Ren, Yi and Kishawy, Mohab and Chen, Jun and Duong, Anh-Kiet and Gomez-Kramer, Petra and Carozza, Jean-Michel and Xing, Wangzhi and Lu, Xin and Gu, Enxuan and Zhang, Jingxi and Chen, Diqi and Yi, Qiaosi and Wei, Bingcai and Li, Wenjie and Tie, Bowen and Guo, Heng and Ma, Zhanyu and Tu, Jiachen and Xu, Guoyi and Jiang, Yaoxin and Liu, Cici and Shi, Yaokun and Garrido Mellado, Paula and Feijoo, Daniel and Garcia Lara, Alvaro and Conde, Marcos V. and Zhu, Zhidong and Xiong, Bangshu and Ou, Qiaofeng and Rao, Zhibo and Li, Wei and Zhang, Zida and Geng, Hui and Xu, Qisheng and Deng, Xuyao and Wang, Changjian and Xu, Kele and Dong, Guanglu and Zhao, Qiyao and Zheng, Tianheng and Li, Chunlei and Mou, Lichao and Ren, Chao and Peng, Chang-De and Tsai, Chieh-Yu and Liu, Guan-Cheng and Kang, Li-Wei and Rajak, Abhishek and Singh, Milan Kumar and Kumar, Ankit and Sonone, Dimple and Upla, Kishor and Raja, Kiran and Zhao, Huilin and Xu, Xing and Chen, Chuan and Lao, Yeming and Xun, Wenjing and Yang, Li and Benjdira, Bilel and Ali, Anas M. and Boulila, Wadii and Yang, Hao and Zhang, Ruikun and Pan, Liyuan},booktitle={Proceedings of the {IEEE/CVF} Conference on Computer Vision and Pattern Recognition ({CVPR}) Workshops},month=jun,year={2026},pages={2054--2070},}
Our team (RetinexDualV2) ranked 5th in Track 2: Joint Denoising and Low-Light Image Enhancement (JDLLIE).
This paper presents a comprehensive review of the NTIRE 2026 Low Light Image Enhancement Challenge, highlighting the proposed solutions and final results. The objective of this challenge is to identify effective networks capable of producing clearer and visually compelling images in diverse and challenging conditions, by learning representative visual cues with the purpose of restoring information loss due to low-contrast and noisy images. A total of 195 participants registered for the first track and 153 for the second track of the competition, and 22 teams ultimately submitted valid entries. This paper thoroughly evaluates the state-of-the-art advances in (joint denoising and) low-light image enhancement, showcasing the significant progress in the field, while leveraging samples of our novel dataset.
@inproceedings{ciubotariu2026ntire_lowlight,title={Low Light Image Enhancement Challenge at {NTIRE} 2026},author={Ciubotariu, George and A, Sharif S M and Rehman, Abdur and Dharejo, Fayaz Ali and Naqvi, Rizwan Ali and Conde, Marcos V and Timofte, Radu and Jin, Zhi and Wu, Hongjun and Zhang, Wenjian and Ye, Chang and Yi, Xunpeng and Yan, Qinglong and Zhang, Yibing and Akalwadi, Nikhil and I Pattanshetty, Varda and I Pattanshetty, Varsha and Desai, Padmashree and Mudenagudi, Uma and Tabib, Ramesh Ashok and Yang, Hao and Zhang, Ruikun and Pan, Liyuan and Kinli, Furkan and Ryou, Donghun and Ha, Inju and Kang, Junoh and Han, Bohyung and Zhou, Wei and Haitman, Yuval and Lapid, Ariel and Peretz, Reuven and Diamant, Idit and Cao, Leilei and Zhang, Shuo and Hambarde, Praful and Shaily, Prateek and Kumar, Jayant and Sharma, Hardik and Negi, Aashish and Chaudhary, Sachin and Dudhane, Akshay and Shukla, Amit and Wu, MoHao and Wang, Lin and Tu, Jiachen and Xu, Guoyi and Jiang, Yaoxin and Liu, Jiajia and Shi, Yaokun and Balmez, Raul and Brateanu, Alexandru and Orhei, Ciprian and Ancuti, Cosmin and Ancuti, Codruta O. and Benjdira, Bilel and Ali, Anas M. and Boulila, Wadii and Qiao, Kaifan and Chen, Bofei and Xu, Jingyi and Zhang, Duo and Deng, Xin and Xu, Mai and Li, Shengxi and Jiang, Lai and A, Harini and N, Ananya and K, Lakshanya and Xu, Ying and Zhu, Xinyi and Shi, Shijun and Zhang, Jiangning and Liu, Yong and Hu, Kai and Xu, Jing and Zeng, Xianfang and Song, Jinao and Tang, Guangsheng and Li, Cheng and Yang, Yuqiang and Wang, Ziyi and Chen, Yan and Bao, Long and Sun, Heng and Kishawy, Mohab and Chen, Jun and Siu, Wan-Chi and Cheng, Yihao and Lee, Man Hammond and Hui, Chun-Chuen},booktitle={Proceedings of the {IEEE/CVF} Conference on Computer Vision and Pattern Recognition ({CVPR}) Workshops},month=jun,year={2026},pages={1741--1753},}
RetinexDualV2 ranked 4th in the NTIRE 2026 Day and Night Raindrop Removal Challenge and 5th in the NTIRE 2026 Joint Denoising and Low-Light Image Enhancement (JDLLIE) track.
We propose RetinexDualV2, a unified, physically grounded dual-branch framework for diverse Ultra-High-Definition (UHD) image restoration. Unlike generic models, our method employs a Task-Specific Physical Grounding Module (TS-PGM) to extract degradation-aware priors (e.g., rain masks and dark channels). These explicitly guide a Retinex decomposition network via a novel Physical-Conditioned Multi-head Self-Attention (PC-MSA) mechanism, enabling robust reflection and illumination correction. This physical conditioning allows a single architecture to handle various complex degradations seamlessly, without task-specific structural modifications. RetinexDualV2 demonstrates exceptional generalizability, securing 4th place in the NTIRE 2026 Day and Night Raindrop Removal Challenge and 5th place in the Joint Noise Low-light Enhancement (JNLLIE) Challenge. Extensive experiments confirm the state-of-the-art performance and efficiency of our physically motivated approach. Code is available at https://github.com/ErrorLogic1211/RetinexDual/tree/master/RetinexDualV2
@inproceedings{kishawy2026retinexdualv2,title={{RetinexDualV2}: Physically-Grounded Dual Retinex for Generalized {UHD} Image Restoration},author={Kishawy, Mohab and Chen, Jun},booktitle={Proceedings of the {IEEE/CVF} Conference on Computer Vision and Pattern Recognition ({CVPR}) Workshops},month=jun,year={2026},pages={1989--1998},}
