High-Resolution Single Image Dehazing Using Encoder-Decoder Architecture

Simone Bianco, Luigi Celona, Flavio Piccoli, Raimondo Schettini

CVPRW 2019 pp. 1927-1935

doi:10.1109/CVPRW.2019.00244 /cvprw/2019/bianco2019cvprw-highresolution/

Abstract

In this work we propose HR-Dehazer, a novel and accurate method for image dehazing. An encoder-decoder neural network is trained to learn a direct mapping between a hazy image and its respective clear version. We designed a special loss that forces the network to keep into account the semantics of the input image and to promote consistency among local structures. In addition, this loss makes the system more invariant to scale changes. Quantitative results on the recently released DenseHaze dataset introduced for the NTIRE2019-Dehazing challenge demonstrates the effectiveness of the proposed method. Furthermore, qualitative results on real data show that the described solution generalizes well to different never-seen scenarios.

CVPRW Semantic Scholar

Cite

Text

Bianco et al. "High-Resolution Single Image Dehazing Using Encoder-Decoder Architecture." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019. doi:10.1109/CVPRW.2019.00244

Markdown

[Bianco et al. "High-Resolution Single Image Dehazing Using Encoder-Decoder Architecture." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019.](https://mlanthology.org/cvprw/2019/bianco2019cvprw-highresolution/) doi:10.1109/CVPRW.2019.00244

BibTeX

@inproceedings{bianco2019cvprw-highresolution,
  title     = {{High-Resolution Single Image Dehazing Using Encoder-Decoder Architecture}},
  author    = {Bianco, Simone and Celona, Luigi and Piccoli, Flavio and Schettini, Raimondo},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2019},
  pages     = {1927-1935},
  doi       = {10.1109/CVPRW.2019.00244},
  url       = {https://mlanthology.org/cvprw/2019/bianco2019cvprw-highresolution/}
}