@InProceedings{PatriciaSuarez2018,
author="Patricia Suarez
and Angel Sappa
and Boris X. Vintimilla
and Riad I. Hammoud",
title="Deep Learning based Single Image Dehazing",
booktitle="31st IEEE Conference on Computer Vision and Pattern Recognition Workhsop",
year="2018",
pages="1250--12507",
optkeywords="Gallium nitride",
optkeywords="Atmospheric modeling",
optkeywords="Generators",
optkeywords="Generative adversarial networks",
optkeywords="Convergence",
optkeywords="Image color analysis",
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 clearimages 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.",
optnote="MSIAU; 600.086; 600.130; 600.122",
optnote="exported from refbase (http://refbase.cvc.uab.es/show.php?record=3197), last updated on Tue, 25 Apr 2023 14:11:48 +0200",
doi="10.1109/CVPRW.2018.00162",
file=":http://refbase.cvc.uab.es/files/SSV2018d.pdf:PDF"
}