NTIRE 2024 Dense and Non-Homogeneous Dehazing Challenge Report

Codruta O. Ancuti, Cosmin Ancuti, Florin-Alexandru Vasluianu, Radu Timofte, Yidi Liu, Xingbo Wang, Yurui Zhu, Gege Shi, Xin Lu, Xueyang Fu, Zheng-Jun Zha, Wei Dong, Han Zhou, Ruiyi Wang, Xiaohong Liu, Guangtao Zhai, Jun Chen, Wei Song, Yichang Gao, Jiahao Xiong, Hualiang Lin, Xianger Li, Dong Li, Mohab Kishawy, Ruibin Li, Seyed Amirreza Mousavi, Rana Rauf, Yangyi Liu, Huan Liu, Mingsheng Tu, Kele Xu, Jiawen Chen, Qisheng Xu, Tao Sun, Jin Guo, Ben Shao, Tianli Liu, Mohao Wu, Xingzhuo Yan, Minghan Fu, Lehan Yang, Xin Lin, Lu Qi, Jincen Song, Xiaoqian Hu, Linwai Tao, Hongming Chen, Xiang Chen, Chuanlong Xie, Zhao Zhang, Junhu Wang, Yanyan Wei, Suiyi Zhao, Shengeng Tang, Sampada Malagi, Amogh Joshi, Nikhil Akalwadi, Chaitra Desai, Ramesh Ashok Tabib, Uma Mudenagudi, Wenjing Jiang, Jagadeesh Kalyanshetti, Vijayalaxmi Ashok Aralikatti, Yashaswini P, Nitish Upasi, Dikshit Hegde, Ujwala Patil, Sujata C; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2024, pp. 6453-6468

Abstract

This study examines the results of the NTIRE 2024 Challenge on Dense and Non-Homogeneous Dehazing. Innovative methods were introduced and tested using a new image dataset named DNH-HAZE. The DNH-HAZE dataset comprises 50 pairs of authentic outdoor images showcasing dense and non-homogeneous haze alongside corresponding haze-free images of identical scenes. The haze was simulated using a professional setup designed to mirror real-world hazy conditions. The competition attracted 374 participants with 16 teams presenting solutions for the final evaluation phase. The proposed solutions showed the leading edge of image dehazing technology.

Related Material

[pdf]
[bibtex]
@InProceedings{Ancuti_2024_CVPR, author = {Ancuti, Codruta O. and Ancuti, Cosmin and Vasluianu, Florin-Alexandru and Timofte, Radu and Liu, Yidi and Wang, Xingbo and Zhu, Yurui and Shi, Gege and Lu, Xin and Fu, Xueyang and Zha, Zheng-Jun and Dong, Wei and Zhou, Han and Wang, Ruiyi and Liu, Xiaohong and Zhai, Guangtao and Chen, Jun and Song, Wei and Gao, Yichang and Xiong, Jiahao and Lin, Hualiang and Li, Xianger and Li, Dong and Kishawy, Mohab and Li, Ruibin and Mousavi, Seyed Amirreza and Rauf, Rana and Liu, Yangyi and Liu, Huan and Tu, Mingsheng and Xu, Kele and Chen, Jiawen and Xu, Qisheng and Sun, Tao and Guo, Jin and Shao, Ben and Liu, Tianli and Wu, Mohao and Yan, Xingzhuo and Fu, Minghan and Yang, Lehan and Lin, Xin and Qi, Lu and Song, Jincen and Hu, Xiaoqian and Tao, Linwai and Chen, Hongming and Chen, Xiang and Xie, Chuanlong and Zhang, Zhao and Wang, Junhu and Wei, Yanyan and Zhao, Suiyi and Tang, Shengeng and Malagi, Sampada and Joshi, Amogh and Akalwadi, Nikhil and Desai, Chaitra and Tabib, Ramesh Ashok and Mudenagudi, Uma and Jiang, Wenjing and Kalyanshetti, Jagadeesh and Aralikatti, Vijayalaxmi Ashok and P, Yashaswini and Upasi, Nitish and Hegde, Dikshit and Patil, Ujwala and C, Sujata}, title = {NTIRE 2024 Dense and Non-Homogeneous Dehazing Challenge Report}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2024}, pages = {6453-6468} }