Capítulo de livro Revisado por pares

Non-homogeneous Haze Removal Through a Multiple Attention Module Architecture

2021; Springer Science+Business Media; Linguagem: Inglês

10.1007/978-3-030-90436-4_14

ISSN

1611-3349

Autores

Patricia L. Suárez, Darío Carpio, Ángel D. Sappa,

Tópico(s)

Advanced Image Processing Techniques

Resumo

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.

Referência(s)