Affiliations: [a] College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao, China
| [b] College of Intelligent Equipment, Shandong University of Science and Technology, Tai’an, China
Correspondence:
[*]
Corresponding author. Hongjuan Wang, College of Intelligent Equipment, Shandong University of Science and Technology, Tai’an, 271000, Shandong Province, China. E-mail: wanghongjuan@sdust.edu.cn.
Abstract: Clear images are generally desirable in high-level computer vision algorithms which are mostly deployed outdoors. However, affected by the changeable weather in the real world, images are inevitably contaminated by rain streaks. Deep convolutional neural networks (CNNs) have shown significant potential in rain streaks removal. The performance of most existing CNN-based deraining methods is often enhanced by stacking vanilla convolutional layers and some other methods use dilated convolution which can only model local pixel relations to provide the necessary but limited receptive field. Therefore, long-range contextual information is rarely considered for this specific task, thus, deraining a single image remains challenging problem. To address the above problem, an effective residual deep attention network (RDANet) for single image rain removal is proposed. Specifically, we design a strong basic unit that contains dilated convolution, spatial and channel attention module (SCAM) simultaneously. As contextual information is very important for rain removal, the proposed basic unit can capture global long-distance dependencies among pixels in feature maps and model feature relations across channels. Compared with a single dilated convolution, the spatial and channel attention enhance the feature expression ability of the network. Moreover, some previous works have proven that the no-rain information in a rain image will be missing during deraining. To enrich the detailed information in the clean images, we present a residual feature processing group (RFPG) that contains several source skip connections to inject rainy shallow source information into each basic unit. In summary, our model can effectively handle complicated long rain streaks in spatial and the outputs of the network can retain most of the details of the original rain images. Experiments demonstrate the superiority of our RDANet over state-of-the-art methods in terms of both quantitative metrics and visual quality on both synthetic and real rainy images.
Keywords: Single image deraining, convolutional neural network, spatial and channel attention, source skip connection
