Semi-Supervised Image Dehazing

Lerenhan Li, Yunlong Dong, Wenqi Ren, Jinshan Pan, Changxin Gao, Nong Sang, Ming-Hsuan Yang

Abstract

We present an effective semi-supervised learning algorithm for single image dehazing. The proposed algorithm applies a deep Convolutional Neural Network (CNN) containing a supervised learning branch and an unsupervised learning branch. In the supervised branch, the deep neural network is constrained by the supervised loss functions, which are mean squared, perceptual, and adversarial losses. In the unsupervised branch, we exploit the properties of clean images via sparsity of dark channel and gradient priors to constrain the network. We train the proposed network on both the synthetic data and real-world images in an end-to-end manner. Our analysis shows that the proposed semi-supervised learning algorithm is not limited to synthetic training datasets and can be generalized well to real-world images. Extensive experimental results demonstrate that the proposed algorithm performs favorably against the state-of-the-art single image dehazing algorithms on both benchmark datasets and real-world images.
BibTeX
@article{li2020semi,
  author = {Lerenhan Li and Yunlong Dong and Wenqi Ren and Jinshan Pan and Changxin Gao and Nong Sang and Ming-Hsuan Yang},
  title = {{Semi-Supervised Image Dehazing}},
  journal = {IEEE Trans. Image Process.},
  year = {2020},
  doi = {10.1109/tip.2019.2952690},
}

Loading related content...

Figure