Resolving Scale Ambiguity Via XSlit Aspect Ratio Analysis

doi:10.1109/ICCV.2015.391

	Resolving Scale Ambiguity Via XSlit Aspect Ratio Analysis
	Yang, Wei 1; Lin, Haiting 1; Kang, Sing Bing 2; Yu, Jingyi1,3
	2015
会议录名称	2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
ISSN	2380-7504
卷号	2015 International Conference on Computer Vision, ICCV 2015
页码	3424-3432
发表状态	已发表
DOI	10.1109/ICCV.2015.391
摘要	In perspective cameras, images of a frontal-parallel 3D object preserve its aspect ratio invariant to its depth. Such an invariance is useful in photography but is unique to perspective projection. In this paper, we show that alternative non-perspective cameras such as the crossed-slit or XSlit cameras exhibit a different depth-dependent aspect ratio (DDAR) property that can be used to 3D recovery. We first conduct a comprehensive analysis to characterize DDAR, infer object depth from its AR, and model recoverable depth range, sensitivity, and error. We show that repeated shape patterns in real Manhattan World scenes can be used for 3D reconstruction using a single XSlit image. We also extend our analysis to model slopes of lines. Specifically, parallel 3D lines exhibit depth-dependent slopes (DDS) on their images which can also be used to infer their depths. We validate our analyses using real XSlit cameras, XSlit panoramas, and catadioptric mirrors. Experiments show that DDAR and DDS provide important depth cues and enable effective single-image scene reconstruction.
出版地	345 E 47TH ST, NEW YORK, NY 10017 USA
会议地点	Santiago, Chile
会议日期	7-13 Dec. 2015
URL	查看原文
收录类别	CPCI ; EI
语种	英语
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000380414100383
出版者	IEEE
EI入藏号	20162502506731
EI主题词	Cameras ; Computer vision ; Image processing ; Image reconstruction
EI分类号	Computer Applications:723.5 ; Photographic Equipment:742.2
WOS关键词	SINGLE IMAGE ; CAMERA
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/2299
专题	信息科学与技术学院_PI研究组_虞晶怡组
通讯作者	Yang, Wei
作者单位	1.Univ Delaware, Newark, DE 19716 USA 2.Microsoft Res, Greater Seattle, WA USA 3.ShanghaiTech Univ, Shanghai, Peoples R China
推荐引用方式 GB/T 7714	Yang, Wei,Lin, Haiting,Kang, Sing Bing,et al. Resolving Scale Ambiguity Via XSlit Aspect Ratio Analysis[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2015:3424-3432.