A Taxonomy and Evaluation of Dense Light Field Depth Estimation Algorithms

doi:10.1109/CVPRW.2017.226

	A Taxonomy and Evaluation of Dense Light Field Depth Estimation Algorithms
	Johannsen, Ole 1; Honauer, Katrin 2; Goldluecke, Bastian 1; Alperovich, Anna 1; Battisti, Federica 3; Bok, Yunsu 4; Brizzi, Michele 3; Carli, Marco 3; Choe, Gyeongmin 5; Diebold, Maximilian 2; Gutsche, Marcel 2; Jeon, Hae-Gon 5; Kweon, In So 5; Park, Jaesik 6; Park, Jinsun 5; Schilling, Hendrik 2; Sheng, Hao 7; Si, Lipeng 8; Strecke, Michael 1; Sulc, Antonin 1; Tai, Yu-Wing 9; Wang, Qing 8; Wang, Ting-Chun 10; Wanner, Sven 11; Xiong, Zhang 7; Yu, Jingyi12 ; Zhang, Shuo 7; Zhu, Hao 8
	2017
会议录名称	2017 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW)
ISSN	2160-7516
卷号	2017-July
页码	1795-1812
发表状态	已发表
DOI	10.1109/CVPRW.2017.226
摘要	This paper presents the results of the depth estimation challenge for dense light fields, which took place at the second workshop on Light Fields for Computer Vision (LF4CV) in conjunction with CVPR 2017. The challenge consisted of submission to a recent benchmark [7], which allows a thorough performance analysis. While individual results are readily available on the benchmark web page http://www.lightfield-analysis.net, we take this opportunity to give a detailed overview of the current participants. Based on the algorithms submitted to our challenge, we develop a taxonomy of light field disparity estimation algorithms and give a report on the current state-of-the-art. In addition, we include more comparative metrics, and discuss the relative strengths and weaknesses of the algorithms. Thus, we obtain a snapshot of where light field algorithm development stands at the moment and identify aspects with potential for further improvement.
出版地	345 E 47TH ST, NEW YORK, NY 10017 USA
会议地点	Honolulu, HI, United states
会议日期	21-26 July 2017
URL	查看原文
收录类别	CPCI ; EI
语种	英语
资助项目	[SFB Transregio 161]
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000426448300219
出版者	IEEE
EI入藏号	20174004236025
EI主题词	Benchmarking ; Computer vision ; Taxonomies ; Websites
EI分类号	Computer Applications:723.5 ; Information Science:903
WOS关键词	PLANE-IMAGE-ANALYSIS
原始文献类型	Proceedings Paper
来源库	IEEE
引用统计	正在获取...
文献类型	会议论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/13239
专题	信息科学与技术学院_PI研究组_虞晶怡组
通讯作者	Johannsen, Ole
作者单位	1.Univ Konstanz, Constance, Germany 2.Heidelberg Univ, Heidelberg, Germany 3.Roma Tre Univ, Rome, Italy 4.ETRI, Daejeon, South Korea 5.Korea Adv Inst Sci & Technol, Daejeon, South Korea 6.Intel Visual Comp Lab, Las Vegas, NV USA 7.Beihang Univ, Beijing, Peoples R China 8.Northwestern Polytech Univ, Xian, Shaanxi, Peoples R China 9.Tencent, Shanghai, Peoples R China 10.Univ Calif Berkeley, Berkeley, CA USA 11.Lumitec, Dusseldorf, Germany 12.ShanghaiTech Univ, Shanghai, Peoples R China
推荐引用方式 GB/T 7714	Johannsen, Ole,Honauer, Katrin,Goldluecke, Bastian,et al. A Taxonomy and Evaluation of Dense Light Field Depth Estimation Algorithms[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2017:1795-1812.