Successive Graph Convolutional Network for Image De-raining

Deep convolutional neural networks (CNNs) have shown their advantages in the single image de-raining task. However, most existing CNNs-based methods utilize only local spatial information without considering long-range contextual information. In this paper, we propose a graph convolutional networks (GCNs)-based model to solve the above problem. We specifically design two graphs to extract representations from new dimensions. The first graph models the global spatial relationship between pixels in the feature, while the second graph models the interrelationship across the channels. By integrating conventional CNNs and our GCNs into a single framework, the proposed method is able to explore comprehensive feature representations from three aspects, i.e., local spatial patterns, global spatial coherence and channel correlation. To better exploit the explored rich feature representations, we further introduce a simple yet effective recurrent operations to perform the de-raining process in a successive manner. Benefiting from the rich information exploration and exploitation, our method achieves state-of-the-art results on both synthetic and real-world data sets.

Automated summary

This paper introduces a graph convolutional networks (GCNs)-based model to address the issue of single image de-raining, utilizing two graphs to extract representations from new dimensions, integrating conventional CNNs and GCNs to explore feature representations, and introducing recurrent operations for successive de-raining processes. The method achieves state-of-the-art results on both synthetic and real-world data sets by benefiting from rich information exploration and exploitation.