Hazy Removal via Graph Convolutional with Attention Network

Most deep learning based single image dehazing methods use convolutional neural networks (CNN) to extract features, however CNN can only capture local features. To address the limitations of CNN, We propose a basic module that combines CNN and graph convolutional network (GCN) to capture both local and non-local features. The basic module consist of a CNN with triple attention modules (CAM) and a dual GCN module (DGM). CAM that combines the channel attention, spatial attention and pixel attention is designed to earn more weight from important local features. DGM combines spatial coherence computing and channel correlation computing to extract non-local information. The architecture of the network is similar to U-Net, and skip connections used in the symmetrical network can pass the image details from shallow layers to deep layers. Experimental results in several datasets indicate that the proposed method outperforms the state-of-the-arts both quantitatively and qualitatively.