View-graph construction framework for robust and efficient structure-from-motion

doi:10.1016/j.patcog.2020.107712

	View-graph construction framework for robust and efficient structure-from-motion
	Cui, Hainan1 ; Shi, Tianxin1 ; Zhang, Jun 2; Xu, Pengfei 2; Meng, Yiping2 ; Shen, Shuhan1,3
发表期刊	PATTERN RECOGNITION
ISSN	0031-3203
	2021-06-01
卷号	114 页码:9
通讯作者	Cui, Hainan(hncui@nlpr.ia.ac.cn)
摘要	A view-graph is vital for both the accuracy and robustness of structure-from-motion (SfM). Conventional matrix decomposition techniques treat all edges of view-graph equally; hence, many edge outliers are produced in matching pairs with fewer feature matches. To address this problem, we propose an incremental framework for view-graph construction, where the robustness of matched pairs that have a larger number of feature matches is propagated to their connected images. Given pairwise feature matches, a verified maximum spanning tree (VMST) is first constructed; for each edge in the VMST, we perform a local reconstruction and register its visible cameras. Based on the local reconstruction, pairwise relative geometries are computed and some new epipolar edges are produced. In this way, these newly computed edges inherit the robustness and accuracy of VMST, and by embedding them into VMST, our view-graph is constructed. We feed our view-graph into a standard SfM pipeline and compare this newly formed system with many of state-of-the-art SfM methods. The experimental results demonstrate that our view graph provides a better foundation for conventional SfM systems, and enables them to reconstruct both general and ambiguous images. ? 2020 Elsevier Ltd. All rights reserved.
关键词	Structure-from-motion View-graph construction Epipolar geometry computation
DOI	10.1016/j.patcog.2020.107712
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61703397] ; National Natural Science Foundation of China[U1805264] ; Didi GAIA Foundation
项目资助者	National Natural Science Foundation of China ; Didi GAIA Foundation
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000625557800001
出版者	ELSEVIER SCI LTD
七大方向——子方向分类	三维视觉
引用统计	被引频次：13[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/43348
专题	多模态人工智能系统全国重点实验室_机器人视觉
通讯作者	Cui, Hainan
作者单位	1.Chinese Acad Sci, Inst Automat, NLPR, Beijing, Peoples R China 2.Didi Chuxing, Beijing, Peoples R China 3.Univ Chinese Acad Sci, Beijing, Peoples R China
第一作者单位	模式识别国家重点实验室
通讯作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Cui, Hainan,Shi, Tianxin,Zhang, Jun,et al. View-graph construction framework for robust and efficient structure-from-motion[J]. PATTERN RECOGNITION,2021,114:9.
APA	Cui, Hainan,Shi, Tianxin,Zhang, Jun,Xu, Pengfei,Meng, Yiping,&Shen, Shuhan.(2021).View-graph construction framework for robust and efficient structure-from-motion.PATTERN RECOGNITION,114,9.
MLA	Cui, Hainan,et al."View-graph construction framework for robust and efficient structure-from-motion".PATTERN RECOGNITION 114(2021):9.