Automatic 3D Indoor Scene Modeling from Single Panorama

doi:10.1109/CVPR.2018.00413

	Automatic 3D Indoor Scene Modeling from Single Panorama
	Yang, Yang 1; Jin, Shi2 ; Liu, Ruiyang2 ; Kang, Sing Bing 4; Yu, Jingyi2,3
	2018
会议录名称	2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
ISSN	1063-6919
页码	3926-3934
发表状态	已发表
DOI	10.1109/CVPR.2018.00413
摘要	We describe a system that automatically extracts 3D geometry of an indoor scene from a single 2D panorama. Our system recovers the spatial layout by finding the floor, walls, and ceiling; it also recovers shapes of typical indoor objects such as furniture. Using sampled perspective sub views, we extract geometric cues (lines, vanishing points, orientation map, and surface normals) and semantic cues (saliency and object detection information). These cues are used for ground plane estimation and occlusion reasoning. The global spatial layout is inferred through a constraint graph on line segments and planar superpixels. The recovered layout is then used to guide shape estimation of the remaining objects using their normal information. Experiments on synthetic and real datasets show that our approach is state-of-the-art in both accuracy and efficiency. Our system can handle cluttered scenes with complex geometry that are challenging to existing techniques.
出版地	345 E 47TH ST, NEW YORK, NY 10017 USA
会议地点	Salt Lake City, UT, United states
会议日期	18-23 June 2018
URL	查看原文
收录类别	CPCI ; CPCI-S ; EI
语种	英语
资助项目	National Science Foundation[HS-1422477]
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000457843604008
出版者	IEEE
EI入藏号	20191106642898
EI主题词	Computer vision ; Geometry ; Object detection ; Object recognition ; Semantics
EI分类号	Data Processing and Image Processing:723.2 ; Computer Applications:723.5 ; Mathematics:921
WOS关键词	LAYOUT
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/29877
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	Yang, Yang
作者单位	1.Univ Delaware, Newark, DE 19716 USA 2.ShanghaiTech Univ, Shanghai, Peoples R China 3.Plex VR Inc, Shanghai, Peoples R China 4.Microsoft Res, Bengaluru, India
推荐引用方式 GB/T 7714	Yang, Yang,Jin, Shi,Liu, Ruiyang,et al. Automatic 3D Indoor Scene Modeling from Single Panorama[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2018:3926-3934.