CASIA OpenIR  > 模式识别国家重点实验室  > 机器人视觉
Fast depth extraction from a single image
He, Lei1; Dong, Qiulei1; Wang, Guanghui2
Source PublicationINTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS
2016-11-14
Volume13Issue:1Pages:1-10
SubtypeArticle
AbstractPredicting depth from a single image is an important problem for understanding the 3-D geometry of a scene. Recently, the nonparametric depth sampling (Depth Transfer) has shown great potential in solving this problem, and its two key components are a Scale Invariant Feature Transform (SIFT) flow-based depth warping between the input image and its retrieved similar images and a pixel-wise depth fusion from all warped depth maps. In addition to the inherent heavy computational load in the SIFT flow computation even under a coarse-to-fine scheme, the fusion reliability is also low due to the low discriminativeness of pixel-wise description nature. This article aims at solving these two problems. First, a novel sparse SIFT flow algorithm is proposed to reduce the complexity from subquadratic to sublinear. Then, a reweighting technique is introduced where the variance of the SIFT flow descriptor is computed at every pixel and used for reweighting the data term in the conditional Markov random fields. Our proposed depth transfer method is tested on the Make3D Range Image Data and NYU Depth Dataset V2. It is shown that, with comparable depth estimation accuracy, our method is 2-3 times faster than the Depth Transfer.
KeywordDepth Extraction Single Image Sparse Sift Flow
WOS HeadingsScience & Technology ; Technology
DOI10.1177/1729881416663370
Indexed BySCI
Language英语
Funding OrganizationStrategic Priority Research Program of the Chinese Academy of Sciences(XDB02070002) ; National Natural Science Foundation of China(61421004 ; 61333015 ; 61573351 ; 61283282)
WOS Research AreaRobotics
WOS SubjectRobotics
WOS IDWOS:000394814200001
Citation statistics
Cited Times:2[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/12442
Collection模式识别国家重点实验室_机器人视觉
Corresponding AuthorDong, Qiulei
Affiliation1.Chinese Acad Sci, Inst Automat, 95 Zhongguancun East Rd, Beijing 100190, Peoples R China
2.Univ Kansas, Dept Elect Engn & Comp Sci, Lawrence, KS 66045 USA
Recommended Citation
GB/T 7714
He, Lei,Dong, Qiulei,Wang, Guanghui. Fast depth extraction from a single image[J]. INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS,2016,13(1):1-10.
APA He, Lei,Dong, Qiulei,&Wang, Guanghui.(2016).Fast depth extraction from a single image.INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS,13(1),1-10.
MLA He, Lei,et al."Fast depth extraction from a single image".INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS 13.1(2016):1-10.
Files in This Item: Download All
File Name/Size DocType Version Access License
Fast depth extractio(2922KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[He, Lei]'s Articles
[Dong, Qiulei]'s Articles
[Wang, Guanghui]'s Articles
Baidu academic
Similar articles in Baidu academic
[He, Lei]'s Articles
[Dong, Qiulei]'s Articles
[Wang, Guanghui]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[He, Lei]'s Articles
[Dong, Qiulei]'s Articles
[Wang, Guanghui]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Fast depth extraction from a single image.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.