Deep convolutional neural networks

Deep convolutional neural networks (CNNs) have becomedominant in the single image de-raining area. However, mostdeep CNNs-based de-raining methods are designed by stacking vanilla convolutional layers, which can only be used tomodel local relations. Therefore, long-range contextual information is rarely considered for this specific task. To address the above problem, we propose a simple yet effectivedual graph convolutional network (GCN) for single imagerain removal. Specifically, we design two graphs to perform global relational modeling and reasoning. The first GCN is used to explore global spatial relations among pixels in feature maps, while the second GCN models the global relations across the channels. Compared to standard convolutional operations, the proposed two graphs enable thenetwork to extract representations from new dimensions. To achieve the image rain removal, we further embed these two graphs and multi-scale dilated convolution into a symmetrically skip-connected network architecture. Therefore, our dual graph convolutional network is able to well handle complex and spatially long rain streaks by exploring multiple representations, e.g., multi-scale local feature, global spatial coherence and cross-channel correlation. Meanwhile, our model is easy to implement, end-to-end trainable and computationally efficient. Extensive experiments on synthetic and real data demonstrate that our method achieves significant improvements over the recent state-of-the-art methods.