Color layers -Based progressive network for Single image dehazing

While deep learning-based dehazing methods have achieved significant success in recent years, most emphasize more on dehazing and less on image color recovery. In this paper, we propose a progressive network incorporating color layers. It gradually recovers the image by repeatedly invoking an auxiliary progressive network. The RGBA image information captured by the soft color segmentation is used as the input for the auxiliary learning. Specifically, we first introduce the gated recurrent unit in the feature extraction module, which can effectively extract image features while preventing model overfitting. Next, local features are extracted in the residual learning module by combining the recurrent layer and residual blocks. Finally composite module integrates the features to produce a clean image with rich details. In addition, recursive computation is used in each stage to reduce network parameters while improving performance. Extensive experimental results demonstrate that the proposed method outperforms the state-of-the-arts quantitatively and qualitatively.