High-fidelity View Synthesis for Light Field Imaging With Extended Pseudo 4DCNN

doi:10.1109/TCI.2020.2986092

CORC > 自动化研究所 > 中国科学院自动化研究所 > 智能感知与计算研究中心

	High-fidelity View Synthesis for Light Field Imaging With Extended Pseudo 4DCNN
	Wang, Yunlong 2; Liu, Fei 2; Zhang, Kunbo 2; Wang, Zilei 1; Sun, Zhenan 2; Tan, Tieniu 2
刊名	IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING
	2020
卷号	6 页码:830-842
关键词	View synthesis light field reconstruction end-to-end structure preserving extended pseudo 4DCNN
ISSN号	2573-0436
DOI	10.1109/TCI.2020.2986092
通讯作者	Sun, Zhenan(znsun@nlpr.ia.ac.cn)
英文摘要	Multi-view properties of light field (LF) imaging enable exciting applications such as auto-refocusing, depth estimation and 3D reconstruction. However, limited angular resolution has become the main bottleneck of microlens-based plenoptic cameras towards more practical vision applications. Existing view synthesis methods mainly break the task into two steps, i.e. depth estimating and view warping, which are usually inefficient and produce artifacts over depth ambiguities. We have proposed an end-to-end deep learning framework named Pseudo 4DCNN to solve these problems in a conference paper. Rethinking on the overall paradigm, we further extend pseudo 4DCNN and propose a novel loss function which is applicable for all tasks of light field reconstruction i.e. EPI Structure Preserving (ESP) loss function. This loss function is proposed to attenuate the blurry edges and artifacts caused by averaging effect of L-2 norm based loss function. Furthermore, the extended Pseudo 4DCNN is compared with recent state-of-the-art (SOTA) approaches on more publicly available light field databases, as well as self-captured light field biometrics and microscopy datasets. Experimental results demonstrate that the proposed framework can achieve better performances than vanilla Pseudo 4DCNN and other SOTA methods, especially in the terms of visual quality under occlusions. The source codes and self-collected datasets for reproducibility will be available online soon.
资助项目	National Natural Science Foundation of China[61427811] ; National Natural Science Foundation of China[61806197] ; National Natural Science Foundation of China[61803372] ; National Key Research and Development Program of China[2016YFB1001000] ; National Key Research and Development Program of China[2017YFB0801900] ; Science and Technology Cooperation Project with Academy of Sichuan Province[18SYXHZ0015] ; Science and Technology Cooperation Project with University of Sichuan Province[18SYXHZ0015]
WOS研究方向	Engineering ; Imaging Science & Photographic Technology
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000560667800005
资助机构	National Natural Science Foundation of China ; National Key Research and Development Program of China ; Science and Technology Cooperation Project with Academy of Sichuan Province ; Science and Technology Cooperation Project with University of Sichuan Province
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/40518]
专题	自动化研究所_智能感知与计算研究中心
通讯作者	Sun, Zhenan
作者单位	1.Univ Sci & Technol China, Hefei, Peoples R China 2.Chinese Acad Sci, Ctr Res Intelligent Percept & Comp, Natl Lab Pattern Recognit Inst Automat, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Wang, Yunlong,Liu, Fei,Zhang, Kunbo,et al. High-fidelity View Synthesis for Light Field Imaging With Extended Pseudo 4DCNN[J]. IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING,2020,6:830-842.
APA	Wang, Yunlong,Liu, Fei,Zhang, Kunbo,Wang, Zilei,Sun, Zhenan,&Tan, Tieniu.(2020).High-fidelity View Synthesis for Light Field Imaging With Extended Pseudo 4DCNN.IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING,6,830-842.
MLA	Wang, Yunlong,et al."High-fidelity View Synthesis for Light Field Imaging With Extended Pseudo 4DCNN".IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING 6(2020):830-842.