Successive Graph Convolutional Network for Image De-raining

Xueyang Fu

doi:10.1007/s11263-020-01428-6

Successive Graph Convolutional Network for Image De-raining

2021-03-02

37

PRE

AI

DOI：10.1007/s11263-020-01428-6

原文链接

原文求助

摘要

En 中文

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.

Keyword:

Image de-raining

Graph convolutional networks

Deep learning

Image processing

Successive Graph Convolutional Network for Image De-raining

摘要

AI总结

期刊

机构