Deep learning for dehazing: Benchmark and analysis

Leonel Cuevas Valeriano , Jean-Baptiste Thomas (1) , A Benoit (2)

1 Le2i - Laboratoire Electronique, Informatique et Image [UMR6306]
2 LISTIC - Laboratoire d'Informatique, Systèmes, Traitement de l'Information et de la Connaissance

We compare a recent dehazing method based on deep learning , Dehazenet, with traditional state-of-the-art approach, on benchmark data with reference. Dehazenet estimates the depth map from 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 this method exhibits the same limitation than other inversions of this imaging model.

Domaines: Traitement du signal et de l'image [eess.SP]; Intelligence artificielle [cs.AI]; Vision par ordinateur et reconnaissance de formes [cs.CV]; Multimédia [cs.MM]; Réseau de neurones [cs.NE]; Machine Learning [stat.ML]

Leonel Cuevas Valeriano, Jean-Baptiste Thomas, A Benoit. Deep learning for dehazing: Benchmark and analysis. NOBIM 2018, Mar 2018, Hafjell, Øyer, Norway. ⟨hal-01786653⟩