%0 Conference Proceedings
%T Non-homogeneous Haze Removal Through a Multiple Attention Module Architecture
%A Patricia Suarez
%A Dario Carpio
%A Angel Sappa
%B 16th International Symposium on Visual Computing
%D 2021
%V 13018
%F Patricia Suarez2021
%O MSIAU
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=3668), last updated on Tue, 24 May 2022 14:48:57 +0200
%X This paper presents a novel attention based architecture to remove non-homogeneous haze. The proposed model is focused on obtaining the most representative characteristics of the image, at each learning cycle, by means of adaptive attention modules coupled with a residual learning convolutional network. The latter is based on the Res2Net model. The proposed architecture is trained with just a few set of images. Its performance is evaluated on a public benchmark—images from the non-homogeneous haze NTIRE 2021 challenge—and compared with state of the art approaches reaching the best result.
%U https://link.springer.com/chapter/10.1007/978-3-030-90436-4_14
%P 178–190