RAID-Net: Region-Aware Image Deblurring Network Under Guidance of the Image Blur Formulation

doi:10.1109/ACCESS.2022.3194032

	RAID-Net: Region-Aware Image Deblurring Network Under Guidance of the Image Blur Formulation
	Liao, Lianjun 1,2,3; Zhang, Zihao 2,3; Xia, Shihong 2,3
	2022
发表期刊	IEEE ACCESS
ISSN	2169-3536
卷号	10 页码:83940-83948
摘要	Image deblurring is a challenging field in computational photography and computer vision. In the deep learning era, deblurring methods boosted with neural networks achieve significant results. However, the existing methods mainly focus on solving specific image deblurring problem, and overlook the origin of the motion blur. In this paper, we revisit how blur occurs, and divide them into three categories, i.e. caused by relative motion between camera and scene, caused by the movement of the object itself and the edges of a blurring image, which may meet discontinuity because of the pixels trajectory sampled outside the image. To address the issues of different blurs in an image, we propose a two-stage neural network for image deblurring named RAID-Net. In order to remove the global blurry region caused by camera movements, we first use a U-shape network to get the coarse deblurred image. Then we leverage an adaptive reasoning module to model the relationship between different blurry regions within one image jointly and remove the other two categories of motion blur. Experiments on two public benchmark datasets demonstrate that our method achieves comparable or better results over the state-of-the-art methods.
关键词	Image restoration Cameras Convolutional neural networks Task analysis Adaptation models Image edge detection Trajectory Attention mechanism graph neural network graph reasoning network image deblur image processing
DOI	10.1109/ACCESS.2022.3194032
收录类别	SCI
语种	英语
资助项目	China National Key Research and Development Program of Science and Technology for Winter Olympics[2020YFF0304701]
WOS研究方向	Computer Science ; Engineering ; Telecommunications
WOS类目	Computer Science, Information Systems ; Engineering, Electrical & Electronic ; Telecommunications
WOS记录号	WOS:000842086000001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：1[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/19455
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Xia, Shihong
作者单位	1.North China Univ Technol, Sch Informat, Dept Comp Sci & Technol, Beijing 100144, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Dept Comp Sci & Technol, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Liao, Lianjun,Zhang, Zihao,Xia, Shihong. RAID-Net: Region-Aware Image Deblurring Network Under Guidance of the Image Blur Formulation[J]. IEEE ACCESS,2022,10:83940-83948.
APA	Liao, Lianjun,Zhang, Zihao,&Xia, Shihong.(2022).RAID-Net: Region-Aware Image Deblurring Network Under Guidance of the Image Blur Formulation.IEEE ACCESS,10,83940-83948.
MLA	Liao, Lianjun,et al."RAID-Net: Region-Aware Image Deblurring Network Under Guidance of the Image Blur Formulation".IEEE ACCESS 10(2022):83940-83948.