-
[pdf]
[bibtex]@InProceedings{Ancuti_2023_CVPR, author = {Ancuti, Codruta O. and Ancuti, Cosmin and Vasluianu, Florin-Alexandru and Timofte, Radu and Zhou, Han and Dong, Wei and Liu, Yangyi and Chen, Jun and Liu, Huan and Li, Liangyan and Wu, Zijun and Dong, Yubo and Li, Yuyan and Qiu, Tian and He, Yu and Lu, Yonghong and Wu, Yinwei and Jiang, Zhenxiang and Liu, Songhua and Yang, Xingyi and Jing, Yongcheng and Benjdira, Bilel and Ali, Anas M. and Koubaa, Anis and Yang, Hao-Hsiang and Chen, I-Hsiang and Chen, Wei-Ting and Huang, Zhi-Kai and Chen, Yi-Chung and Hsieh, Chia-Hsuan and Chang, Hua-En and Chiang, Yuan-Chun and Kuo, Sy-Yen and Guo, Yu and Gao, Yuan and Liu, Ryan Wen and Lu, Yuxu and Qu, Jingxiang and He, Shengfeng and Ren, Wenqi and Hoang, Trung and Zhang, Haichuan and Yazdani, Amirsaeed and Monga, Vishal and Yang, Lehan and Wu, Alex Jiahao and Mai, Tiancheng and Cong, Xiaofeng and Yin, Xuemeng and Yin, Xuefei and Emad, Hazim and Abdallah, Ahmed and Yasser, Yahya and Elshahat, Dalia and Elbaz, Esraa and Li, Zhan and Kuang, Wenqing and Luo, Ziwei and Gustafsson, Fredrik K. and Zhao, Zheng and Sj\"olund, Jens and Sch\"on, Thomas B. and Zhang, Zhao and Wei, Yanyan and Wang, Junhu and Zhao, Suiyi and Zheng, Huan and Guo, Jin and Sun, Yangfan and Liu, Tianli and Hao, Dejun and Jiang, Kui and Sarvaiya, Anjali and Prajapati, Kalpesh and Patra, Ratnadeep and Barik, Pragnesh and Rathod, Chaitanya and Upla, Kishor and Raja, Kiran and Ramachandra, Raghavendra and Busch, Christoph}, title = {NTIRE 2023 HR NonHomogeneous Dehazing Challenge Report}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2023}, pages = {1808-1825} }
NTIRE 2023 HR NonHomogeneous Dehazing Challenge Report
Abstract
This study assesses the outcomes of the NTIRE 2023 Challenge on Non-Homogeneous Dehazing, wherein novel techniques were proposed and evaluated on new image dataset called HD-NH-HAZE. The HD-NH-HAZE dataset contains 50 high resolution pairs of real-life outdoor images featuring nonhomogeneous hazy images and corresponding haze-free images of the same scene. The nonhomogeneous haze was simulated using a professional setup that replicated real-world conditions of hazy scenarios. The competition had 246 participants and 17 teams that competed in the final testing phase, and the proposed solutions demonstrated the cutting-edge in image dehazing technology.
Related Material