NTIRE Workshop and Challenges @ CVPR 2019
Outdoor Image Dehazing Challenge
Single image dehazing is an ill-posed problem that has recently drawn important attention. Despite the significant increase in interest shown for dehazing over the past few years, the validation of the dehazing methods remains largely unsatisfactory, due to the lack of pairs of real hazy and corresponding haze-free reference images. To address this limitation, we introduce Dense-Haze a novel dehazing dataset. Characterized by dense and homogeneous hazy scenes, Dense-Haze contains 33 pairs of real hazy and corresponding haze-free images of various outdoor scenes. The hazy scenes have been recorded by introducing real haze, generated by professional haze machines. The hazy and haze-free corresponding scenes contain the same visual content captured under the same illumination parameters. Dense-Haze dataset aims to push significantly the state-of-the-art in single-image dehazing by promoting robust methods for real and various hazy scenes. We also provide a comprehensive qualitative and quantitative evaluation of state-of-the-art single image dehazing techniques based on the Dense-Haze dataset. Not surprisingly, our study (using traditional image quality metrics such as PSNR, SSIM and CIEDE2000) reveals that the existing dehazing techniques perform poorly for dense homogeneous hazy scenes and that there is still much room for improvement.
NTIRE is a CVPR workshop that aims to provide an overview of the new trends and advances in those areas. Moreover, it offers an opportunity for academic and industrial attendees to interact and explore collaborations. Jointly with workshop NTIRE organised in 2019 the second image dehazing online challenge.

Dense-Haze has been employed in the dehazing challenge of the NTIRE 2019 CVPR workshop.
DENSE-HAZE: A BENCHMARK FOR IMAGE DEHAZING WITH DENSE-HAZE AND HAZE-FREE IMAGES
Codruta O. Ancuti
Cosmin Ancuti
Radu Timofte
Mateu Sbert
Bibtex

@inproceedings{Dense-Haze_2019,
author = {Codruta O. Ancuti and Cosmin Ancuti and Mateu Sbert and Radu Timofte},
title = {Dense haze: A benchmark for image dehazing with dense-haze and haze-free images},
booktitle =  {IEEE International Conference on Image Processing (ICIP) },
series = {IEEE ICIP 2019},
year = {2019},
location = {Taipei, Taiwan},
}



@inproceedings{NTIRE_Dehazing_2019,
author = {Codruta O Ancuti and Cosmin Ancuti and Radu Timofte and Luc Van Gool and Lei Zhang and Ming-Hsuan Yang},
title = {NTIRE 2019 Image Dehazing Challenge Report},
booktitle =  {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops},
series = {IEEE CVPR 2019},
year = {2019},
location = {Long Beach, US},
}



Download DENSE-HAZE dataset (245 MB)
How to cite DENSE-HAZE dataset:

We grant permission to use and publish all images  on this website. However, if you use our DENSE-HAZE dataset, please cite  the papers:



[1] C.O. Ancuti, C. Ancuti, M. Sbert, R. Timofte "Dense haze: A benchmark for image dehazing with dense-haze and haze-free images", IEEE International Conference on Image Processing (ICIP), 2019

[2] Codruta O Ancuti and Cosmin Ancuti and Radu Timofte and Luc Van Gool and Lei Zhang and Ming-Hsuan Yang "NTIRE 2019 Image Dehazing Challenge Report", IEEE CVPR Workshop, 2019