动态感受野特征选择去雾网络  

Dynamic Receptive Field Feature Selection Dehazing Network

作　　者：查俊伟 张洪艳[1] ZHA Junwei;ZHANG Hongyan(State Key Laboratory of Information Engineering in Surveying,Mapping and Remote Sensing,Wuhan University,Wuhan 430079,China)

机构地区：[1]武汉大学测绘遥感信息工程国家重点实验室,湖北武汉430079

出　　处：《电子科技》2023年第7期56-63,共8页Electronic Science and Technology

基　　金：国家自然科学基金(61871298)。

摘　　要：基于深度学习的去雾模型大多在网络参数固定后,感受野也就随之固定。这导致去雾网络无法针对每个具体的场景采用最优的模式进行去雾,从而造成结果中存在模糊和失真。针对这些问题,文中提出动态感受野特征选择去雾网络。该网络以带有空洞卷积的特征注意力空洞模块为基础组件,并行使用多个空洞率不同的特征注意力空洞模块来提取多尺度特征,并进行动态特征融合,构成动态感受野模块。文中将多个动态感受野模块搭配残差连接组成深度网络,对不同层次的特征进行动态混合,最终解码得到去雾图像。实验结果表明,文中所提算法对室内和室外的合成雾图以及真实含雾图像均具有良好的去雾效果,可以生成清晰、自然的去雾图像。Most of the deep-learning based dehazing models have fixed receptive filed after the parameter are fixed.As a result,the dehazing network cannot adopt the optimal mode for dehazing each specific scene,resulting in ambiguity and distortion in the results.In view of these problems,this study proposes a dynamic receptive field feature selection dehazing network.A feature-attention atrous block with atrous convolution is designed as the basic module of the network.Multiple feature attention atrous blocks with different atrous rates are used in parallel to extract multi-scale features.Dynamic feature fusion is performed on these features to form a dynamic receptive field block.Multiple dynamic receptive field blocks are combined with residual connections to form a deep network.The features from different levels are dynamically mixed and decoded to obtain a haze-free image.The experimental results show that the proposed algorithm has a good dehazing performance on indoor,outdoor,and real hazy images,and can generate clear and natural dehazing images.

关 键 词：图像去雾 动态感受野 多尺度特征 动态特征融合 空洞卷积 自注意力机制 动态神经网络 动态参数 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]