ML Anthology

Single Image Haze Removal Using Dark Channel Prior

Kaiming He, Jian Sun, Xiaoou Tang
CVPR 2009 pp. 1956-1963
doi:10.1109/CVPR.2009.5206515 /cvpr/2009/he2009cvpr-single/

Abstract

In this paper, we propose a simple but effective image prior - dark channel prior to remove haze from a single input image. The dark channel prior is a kind of statistics of the haze-free outdoor images. It is based on a key observation - most local patches in haze-free outdoor images contain some pixels which have very low intensities in at least one color channel. Using this prior with the haze imaging model, we can directly estimate the thickness of the haze and recover a high quality haze-free image. Results on a variety of outdoor haze images demonstrate the power of the proposed prior. Moreover, a high quality depth map can also be obtained as a by-product of haze removal.

CVPR Semantic Scholar

Cite

Text

He et al. "Single Image Haze Removal Using Dark Channel Prior." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2009. doi:10.1109/CVPR.2009.5206515

Markdown

[He et al. "Single Image Haze Removal Using Dark Channel Prior." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2009.](https://mlanthology.org/cvpr/2009/he2009cvpr-single/) doi:10.1109/CVPR.2009.5206515

BibTeX

@inproceedings{he2009cvpr-single,
  title     = {{Single Image Haze Removal Using Dark Channel Prior}},
  author    = {He, Kaiming and Sun, Jian and Tang, Xiaoou},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2009},
  pages     = {1956-1963},
  doi       = {10.1109/CVPR.2009.5206515},
  url       = {https://mlanthology.org/cvpr/2009/he2009cvpr-single/}
}