Feed-Net: Fully End-to-End Dehazing

Shengdong Zhang, Wenqi Ren, Jian Yao

Abstract

This paper proposes an image dehazing model built with a fully convolutional neural network (CNN), called Fully End-to-End Dehazing Network (FEED-Net). In contrast to estimate the transmission map and the atmospheric light separately as most previous deep learning methods, FEED-Net recovers the hazy-free image directly from a hazy image via a light-weight CNN. In addition, we introduce contextual information into dehazing via dilated convolution and use dense skip connection for feature fusion, which makes end-to-end dehazing possible. Experimental results show our method outperforms the state-of-the-art algorithms on both synthetic dataset and real-world images.
BibTeX
@inproceedings{zhang2018feed,
  author = {Shengdong Zhang and Wenqi Ren and Jian Yao},
  title = {{Feed-Net: Fully End-to-End Dehazing}},
  booktitle = {ICME},
  year = {2018},
  doi = {10.1109/icme.2018.8486435},
}

Loading related content...

Figure