Skip to Main content Skip to Navigation
Conference papers

Deep learning for dehazing: Benchmark and analysis

Abstract : 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.
Complete list of metadatas

Cited literature [8 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01786653
Contributor : Alexandre Benoit <>
Submitted on : Sunday, May 6, 2018 - 3:30:44 PM
Last modification on : Monday, March 30, 2020 - 8:41:46 AM
Document(s) archivé(s) le : Tuesday, September 25, 2018 - 6:57:06 AM

File

2018NOBIM.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01786653, version 1

Citation

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

Share

Metrics

Record views

189

Files downloads

158