基于注意机制的轻量化稠密连接网络单幅图像去雨  

Lightweight densely connected network based on attention mechanism for single-image deraining

作　　者：柴国强[1] 王大为[1] 芦宾 李竹[1] CHAI Guoqiang;WANG Dawei;LU Bin;LI Zhu(College of Physics and Information Engineering,Shanxi Normal University,Linfen 041000,China)

机构地区：[1]山西师范大学物理与信息工程学院,临汾041000

出　　处：《北京航空航天大学学报》2022年第11期2186-2192,共7页Journal of Beijing University of Aeronautics and Astronautics

基　　金：国家自然科学基金(62201333,62004119);山西省基础研究计划(20210302124647)。

摘　　要：图像中附着的雨条纹对背景造成的破坏严重影响了对图像信息的分析和后续研究。为了恢复被雨条纹破坏的背景纹理特征,提出一种基于注意机制的轻量化稠密连接网络针对单幅图像进行去雨。注意机制有利于网络准确定位降雨区域,稠密连接网络的使用增强了特征的复用,缓解了梯度消失和模型退化问题。利用多尺度通道混洗深度可分离卷积实现网络轻量化设计,降低了网络参数规模,提升了网络运行效率。在合成数据集和真实数据集上的去雨结果表明,所提算法在定量指标和定性分析上都优于现有算法。The rain streaks attached to the image seriously affect the analysis and follow-up research of the image information.To restore the background texture damaged by rain streaks,this paper proposes a lightweight densely connected network based on attention mechanism to remove rain from a single image.The attention mechanism makes the network locate in the rain streaks area accurately,and the densely connected network enhances the feature reuse,alleviates the gradient disappearance and model degradation problems.The utilization of multi-scale mix channel depthwise separable convolutions realizes lightweight design by reducing the scale of network parameters and enhancing the efficiency of network operation.Both qualitative and quantitative validations on synthetic and real-world datasets demonstrate that the proposed approach can achieve competitive performance in comparison with the state-of-the-art methods.

关 键 词：注意机制 稠密连接网络 轻量化设计 图像去雨 深度学习 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]