The Community for Technology Leaders
2017 30th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) (2017)
Niterói, Rio de Janeiro, Brazil
Oct. 17, 2017 to Oct. 20, 2017
ISSN: 2377-5416
ISBN: 978-1-5386-2219-3
pp: 436-441
ABSTRACT
Image dehazing can be described as the problem of mapping from a hazy image to a haze-free image. Most approaches to this problem use physical models based on simplifications and priors. In this work we demonstrate that a convolutional neural network with a deep architecture and a large image database is able to learn the entire process of dehazing, without the need to adjust parameters, resulting in a much more generic method. We evaluate our approach applying it to real scenes corrupted by haze. The results show that even though our network is trained with simulated indoor images, it is capable of dehazing real outdoor scenes, learning to treat the degradation effect itself, not to reconstruct the scene behind it.
INDEX TERMS
convolution, image colour analysis, image enhancement, image restoration, learning (artificial intelligence), neural nets
CITATION

L. T. Goncalves, J. D. Gaya, P. Drews and S. S. Botelho, "DeepDive: An End-to-End Dehazing Method Using Deep Learning," 2017 30th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), Niterói, Rio de Janeiro, Brazil, 2017, pp. 436-441.
doi:10.1109/SIBGRAPI.2017.64
165 ms
(Ver 3.3 (11022016))