Deep Learning Based Single Image Dehazing

Patricia L. Suarez, Angel Domingo Sappa, Boris Xavier Vintimilla, Riad I. Hammoud

CVPRW 2018 pp. 1169-1176

doi:10.1109/CVPRW.2018.00162 /cvprw/2018/suarez2018cvprw-deep/

Abstract

This paper proposes a novel approach to remove haze degradations in RGB images using a stacked conditional Generative Adversarial Network (GAN). It employs a triplet of GAN to remove the haze on each color channel independently. A multiple loss functions scheme, applied over a conditional probabilistic model, is proposed. The proposed GAN architecture learns to remove the haze, using as conditioned entrance, the images with haze from which the clear images will be obtained. Such formulation ensures a fast model training convergence and a homogeneous model generalization. Experiments showed that the proposed method generates high-quality clear images.

CVPRW Semantic Scholar

Cite

Text

Suarez et al. "Deep Learning Based Single Image Dehazing." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2018. doi:10.1109/CVPRW.2018.00162

Markdown

[Suarez et al. "Deep Learning Based Single Image Dehazing." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2018.](https://mlanthology.org/cvprw/2018/suarez2018cvprw-deep/) doi:10.1109/CVPRW.2018.00162

BibTeX

@inproceedings{suarez2018cvprw-deep,
  title     = {{Deep Learning Based Single Image Dehazing}},
  author    = {Suarez, Patricia L. and Sappa, Angel Domingo and Vintimilla, Boris Xavier and Hammoud, Riad I.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2018},
  pages     = {1169-1176},
  doi       = {10.1109/CVPRW.2018.00162},
  url       = {https://mlanthology.org/cvprw/2018/suarez2018cvprw-deep/}
}