AIF-LFNet: All-in-Focus Light Field Super-Resolution Method Considering the Depth-Varying Defocus

doi:10.1109/TCSVT.2023.3237593

CORC > 自动化研究所 > 中国科学院自动化研究所 > 多模态人工智能系统全国重点实验室

	AIF-LFNet: All-in-Focus Light Field Super-Resolution Method Considering the Depth-Varying Defocus
	Zhou, Shubo 3; Hu, Liang 2; Wang, Yunlong 1; Sun, Zhenan 1; Zhang, Kunbo 1; Jiang, Xue-Qin 3
刊名	IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
	2023-08-01
卷号	33 期号:8 页码:3976-3988
关键词	Light field imaging super-resolution depth-varying defocus dataset convolutional neural network
ISSN号	1051-8215
DOI	10.1109/TCSVT.2023.3237593
通讯作者	Sun, Zhenan(znsun@nlpr.ia.ac.cn)
英文摘要	As an aperture-divided computational imaging system, microlens array (MLA) -based light field (LF) imaging is playing an increasingly important role in computer vision. As the trade-off between the spatial and angular resolutions, deep learning (DL) -based image super-resolution (SR) methods have been applied to enhance the spatial resolution. However, in existing DL-based methods, the depth-varying defocus is not considered both in dataset development and algorithm design, which restricts many applications such as depth estimation and object recognition. To overcome this shortcoming, a super-resolution task that reconstructs all-in-focus high-resolution (HR) LF images from low-resolution (LR) LF images is proposed by designing a large dataset and proposing a convolutional neural network (CNN) -based SR method. The dataset is constructed by using Blender software, consisting of 150 light field images used as training data, and 15 light field images used as validation and testing data. The proposed network is designed by proposing the dilated deformable convolutional network (DCN) -based feature extraction block and the LF subaperture image (SAI) Deblur-SR block. The experimental results demonstrate that the proposed method achieves more appealing results both quantitatively and qualitatively.
资助项目	National Natural Science Foundation of China[61803372] ; National Natural Science Foundation of China[61806197] ; National Natural Science Foundation of China[U1836217] ; National Natural Science Foundation of China[62006225] ; National Natural Science Foundation of China[62071468] ; Fundamental Research Funds for the Central Universities[2232021D-34]
WOS关键词	RECONSTRUCTION ; DECONVOLUTION ; NETWORK
WOS研究方向	Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:001045167400034
资助机构	National Natural Science Foundation of China ; Fundamental Research Funds for the Central Universities
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/53966]
专题	多模态人工智能系统全国重点实验室
通讯作者	Sun, Zhenan
作者单位	1.Chinese Acad Sci CASIA, Inst Automat, Ctr Res Intelligent Percept & Comp, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China 2.Aerosp Informat Res Inst, Chinese Acad Sci, Key Lab Computat Opt Imaging Technol, Beijing Beijing, Peoples R China 3.Donghua Univ, Inst Informat Sci & Technol, Shanghai 201620, Peoples R China
推荐引用方式 GB/T 7714	Zhou, Shubo,Hu, Liang,Wang, Yunlong,et al. AIF-LFNet: All-in-Focus Light Field Super-Resolution Method Considering the Depth-Varying Defocus[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2023,33(8):3976-3988.
APA	Zhou, Shubo,Hu, Liang,Wang, Yunlong,Sun, Zhenan,Zhang, Kunbo,&Jiang, Xue-Qin.(2023).AIF-LFNet: All-in-Focus Light Field Super-Resolution Method Considering the Depth-Varying Defocus.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,33(8),3976-3988.
MLA	Zhou, Shubo,et al."AIF-LFNet: All-in-Focus Light Field Super-Resolution Method Considering the Depth-Varying Defocus".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 33.8(2023):3976-3988.