Deep learning for dehazing: Comparison and analysis

Abstract : We compare a recent dehazing method based on deep learning, Dehazenet, with traditional state-of-the-art approaches , on benchmark data with reference. Dehazenet estimates the depth map from transmission factor on a single color image, which is used to inverse the Koschmieder model of imaging in the presence of haze. In this sense, the solution is still attached to the Koschmieder model. We demonstrate that the transmission is very well estimated by the network, but also that this method exhibits the same limitation than others due to the use of the same imaging model.
Liste complète des métadonnées
Contributeur : Alexandre Benoit <>
Soumis le : mercredi 27 juin 2018 - 22:59:46
Dernière modification le : vendredi 21 septembre 2018 - 14:30:05
Document(s) archivé(s) le : mercredi 26 septembre 2018 - 22:26:43


Fichiers produits par l'(les) auteur(s)


  • HAL Id : hal-01823911, version 1
  • ARXIV : 1806.10923


A Benoit, Leonel Cuevas, Jean-Baptiste Thomas. Deep learning for dehazing: Comparison and analysis. Colour and Visual Computing Symposium (CVCS), Sep 2018, Gjøvik, Norway. 〈hal-01823911〉



Consultations de la notice


Téléchargements de fichiers