首页|基于特征聚合和传播网络的图像超分辨率重建

基于特征聚合和传播网络的图像超分辨率重建

扫码查看
原文链接
  • 万方数据
  • 维普
基于深度学习的图像超分辨率重建通过网络加深提升图像重建性能,但复杂网络会导致参数量急剧增加,限制其在资源受限设备上的应用.针对此问题,文中提出基于特征聚合和传播网络的图像超分辨率重建方法,采用逐步提取融合特征的方式获取图像丰富的内部信息.首先,提出上下文交互注意力模块,使网络学习到特征图丰富的上下文信息,提高特征的利用率.然后,设计多维注意力增强模块,提高网络对关键特征的判别能力,分别在通道和空间两个维度提取高频信息.最后,提出特征聚合传播模块,有效聚合深层细节信息,去除冗余信息,并促进有效信息在网络中传播.在Set5、Set14、BSD100、Urban100等基准数据集上的测试实验表明,文中方法性能较优,重建后的图像细节纹理较清晰.
Image Super-Resolution Reconstruction Based on Feature Aggregation and Propagation Network
Image super-resolution reconstruction based on deep learning improves the image reconstruction performance by deepening the network.However,its application on resource-limited devices is limited due to the sharp increase in the number of parameters caused by complex networks.To solve this problem,an image super-resolution reconstruction method based on feature aggregation and propagation network is proposed,enriching internal information of images by extracting and fusing features step by step.Firstly,a contextual interaction attention block is proposed to enable the network to learn the rich contextual information of feature maps as well as improve the utilization of features.Then,a multi-dimensional attention enhancement block is designed to improve the network's ability to discriminate the key features and extract high-frequency information in channel dimension and spatial dimension,respectively.Finally,a feature aggregation and propagation block is proposed to effectively aggregate deep detail information,remove redundant information and promote the propagation of effective information in the network.Experimental results on Set5,Set14,BSD100 and Urban100 datasets demonstrate the superiority of the proposed method with clearer details of reconstructed images.

Image Super-Resolution ReconstructionConvolutional Neural NetworkContextual Inter-action AttentionMulti-dimensional AttentionFeature Aggregation

薄阳瑜、刘晓晶、武永亮、王学军

展开 >

石家庄铁道大学信息科学与技术学院 石家庄 050043

图像超分辨率重建 卷积神经网络 上下文交互注意力 多维注意力 特征聚合

国家自然科学基金河北省自然科学基金山西省重点实验室开放基金

62106157F2021210002CICIP2022001

2024

10.16451/j.cnki.issn1003-6059.202404002

模式识别与人工智能
中国自动化学会,国家智能计算机研究开发中心,中国科学院合肥智能机械研究所

模式识别与人工智能

CSTPCD北大核心
影响因子：0.954
ISSN：1003-6059
年,卷(期)：2024.37(4)
  • 38