Attention hierarchical network for super-resolution

doi:10.1007/s11042-023-15782-3

	Attention hierarchical network for super-resolution
	Song, Zhaoyang 1; Zhao, Xiaoqiang1,2,3 ; Hui, Yongyong1,2,3 ; Jiang, Hongmei1,2,3
	2023-05-10
在线发表时间	2023-05
发表期刊	MULTIMEDIA TOOLS AND APPLICATIONS
ISSN	1380-7501
摘要	Deep neural networks with attention mechanism for super-resolution (SR) have achieved good SR performance by focusing on the high-frequency components of images. However, during the SR process, it is difficult for these networks to obtain multi-level high-frequency features with different extraction difficulties from low-resolution images, resulting in the lack of textures and details in the reconstructed SR images. To solve this problem, we propose an attention hierarchical network (AHN) for SR. The proposed AHN separates and extracts high-frequency features with different extraction difficulties in a hierarchical way to obtain multi-level high-frequency features. In the process of separation and extraction, we separate high-frequency features into easy-to-extract features and difficult-to-extract features by attention block and extract the separated features by dense-residual module. Extensive experiments demonstrate that the proposed AHN is superior to the state-of-the-art SR methods and reconstructs better SR images that contain more textures and details.
关键词	Super-resolution Deep neural network Attention hierarchical network High-frequency features
DOI	10.1007/s11042-023-15782-3
收录类别	SCIE
语种	英语
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Information Systems ; Computer Science, Software Engineering ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号	WOS:000985244300002
出版者	SPRINGER
来源库	WOS
原始文献类型	Article; Early Access
引用统计	被引频次[WOS]：0 [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	https://ir.lut.edu.cn/handle/2XXMBERH/162109
专题	电气工程与信息工程学院
作者单位	1.Lanzhou Univ Technol, Coll Elect Engn & Informat Engn, Lanzhou 730050, Peoples R China; 2.Key Lab Gansu Adv Control Ind Proc, Lanzhou 730050, Peoples R China; 3.Lanzhou Univ Technol, Natl Expt Teaching Ctr Elect & Control Engn, Lanzhou 730050, Peoples R China
第一作者单位	电气工程与信息工程学院
第一作者的第一单位	电气工程与信息工程学院
推荐引用方式 GB/T 7714	Song, Zhaoyang,Zhao, Xiaoqiang,Hui, Yongyong,et al. Attention hierarchical network for super-resolution[J]. MULTIMEDIA TOOLS AND APPLICATIONS,2023.
APA	Song, Zhaoyang,Zhao, Xiaoqiang,Hui, Yongyong,&Jiang, Hongmei.(2023).Attention hierarchical network for super-resolution.MULTIMEDIA TOOLS AND APPLICATIONS.
MLA	Song, Zhaoyang,et al."Attention hierarchical network for super-resolution".MULTIMEDIA TOOLS AND APPLICATIONS (2023).