Ray Space Features for Plenoptic Structure-from-Motion

doi:10.1109/ICCV.2017.496

	Ray Space Features for Plenoptic Structure-from-Motion
	Zhang, Yingliang1 ; Yu, Peihong1 ; Yang, Wei 2,3; Ma, Yuanxi1 ; Yu, Jingyi1,3
	2017
会议录名称	2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
卷号	2017-October
页码	4641-4649
发表状态	已发表
DOI	10.1109/ICCV.2017.496
摘要	Traditional Structure-from-Motion (SfM) uses images captured by cameras as inputs. In this paper, we explore using light fields captured by plenoptic cameras or camera arrays as inputs. We call this solution plenoptic SfM or P-SfM solution. We first present a comprehensive theory on ray geometry transforms under light field pose variations. We derive the transforms of three typical ray manifolds: rays passing through a point or point-ray manifold, rays passing through a 3D line or ray-line manifold, and rays lying on a common 3D plane or ray-plane manifold. We show that by matching these manifolds across LFs, we can recover light field poses and conduct bundle adjustment in ray space. We validate our theory and framework on synthetic and real data on light fields of different scales: small scale LFs acquired using a LF camera and large scale LFs by a camera array. We show that our P-SfM technique can significantly improve the accuracy and reliability over regular SfM and PnP especially on traditionally challenging scenes where reliable feature point correspondences are difficult to obtain but line or plane correspondences are readily accessible.
出版地	345 E 47TH ST, NEW YORK, NY 10017 USA
会议地点	Venice, Italy
收录类别	CPCI ; EI
语种	英语
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000425498404075
出版者	IEEE
EI入藏号	20180704803696
EI主题词	Computer vision
EI分类号	Computer Applications:723.5 ; Photographic Equipment:742.2
原始文献类型	Proceedings Paper
引用统计
文献类型	会议论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/16305
专题	信息科学与技术学院信息科学与技术学院_PI研究组_虞晶怡组信息科学与技术学院_硕士生信息科学与技术学院_博士生
通讯作者	Zhang, Yingliang
作者单位	1.ShanghaiTech Univ, Shanghai, Peoples R China 2.Univ Delaware, Newark, DE 19716 USA 3.Plex VR Inc, San Jose, CA USA
第一作者单位	上海科技大学
通讯作者单位	上海科技大学
第一作者的第一单位	上海科技大学
推荐引用方式 GB/T 7714	Zhang, Yingliang,Yu, Peihong,Yang, Wei,et al. Ray Space Features for Plenoptic Structure-from-Motion[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2017:4641-4649.