Deep learning-based low overlap point cloud registration for complex scenario: The review

doi:10.1016/j.inffus.2024.102305

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 三维可视计算

	Deep learning-based low overlap point cloud registration for complex scenario: The review
	Zhao, Yuehua 1,2; Zhang, Jiguang3 ; Xu, Shibiao2 ; Ma, Jie 1
发表期刊	INFORMATION FUSION
ISSN	1566-2535
	2024-07-01
卷号	107 页码:23
通讯作者	Xu, Shibiao(shibiaoxu@bupt.edu.cn) ; Ma, Jie(jma@hebut.edu.cn)
摘要	Most studies on point cloud registration have established the problem in the case of ideal point cloud data. Although the state-of-the-art approaches have achieved amazing results on multiple public datasets, the issue of low overlap point cloud data invalidating state-of-the-art methods is acting as a latent challenge that has not been solved. Therefore, a profound analysis about why existing registration architectures break down in the low-overlap regime and how to select the appropriate strategies to improve the low overlap point cloud correspondence estimation is necessary and useful. Unfortunately, there are few survey works about low overlap cloud registration solving strategies and the corresponding datasets are very limited. This work briefly reviews mainstream deep learning-based point cloud registration and provides an in-depth analysis of the reasons why these architectures are not generalizable to scenarios with low overlapping areas. It is the first survey that mainly focuses on representative low overlap registration methods, their techniques, and related datasets for training/testing. It is worth noting that we also design and construct a large 3D dataset to eliminate the gap in Semantic-assisted point cloud registration with low overlap. Finally, challenges about low overlap point cloud registration and future directions in addressing these challenges are also pointed out. [dataset]
关键词	Point cloud registration Low overlap Dataset construction Deep learning-based Survey
DOI	10.1016/j.inffus.2024.102305
关键词[WOS]	NETWORK
收录类别	SCI
语种	英语
资助项目	Beijing Natural Science Foundation[JQ23014] ; National Natural Science Foundation of China[62271074] ; National Natural Science Foundation of China[62171321] ; National Natural Science Foundation of China[62162044] ; National Natural Science Foundation of China[52175493] ; National Natural Science Foundation of China[32271983] ; Open Project Program of State Key Laboratory of Virtual Reality Technology and Systems, Beihang University[VRLAB2023B01]
项目资助者	Beijing Natural Science Foundation ; National Natural Science Foundation of China ; Open Project Program of State Key Laboratory of Virtual Reality Technology and Systems, Beihang University
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Theory & Methods
WOS记录号	WOS:001195207100001
出版者	ELSEVIER
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/57993
专题	多模态人工智能系统全国重点实验室_三维可视计算
通讯作者	Xu, Shibiao; Ma, Jie
作者单位	1.Hebei Univ Technol, Sch Elect & Informat Engn, Tianjin 300401, Peoples R China 2.Beijing Univ Posts & Telecommun, Sch Artificial Intelligence, Beijing 100876, Peoples R China 3.Chinese Acad Sci, Inst Automat, Beijing 100090, Peoples R China
推荐引用方式 GB/T 7714	Zhao, Yuehua,Zhang, Jiguang,Xu, Shibiao,et al. Deep learning-based low overlap point cloud registration for complex scenario: The review[J]. INFORMATION FUSION,2024,107:23.
APA	Zhao, Yuehua,Zhang, Jiguang,Xu, Shibiao,&Ma, Jie.(2024).Deep learning-based low overlap point cloud registration for complex scenario: The review.INFORMATION FUSION,107,23.
MLA	Zhao, Yuehua,et al."Deep learning-based low overlap point cloud registration for complex scenario: The review".INFORMATION FUSION 107(2024):23.