An Accurate Outlier Rejection Network With Higher Generalization Ability for Point Cloud Registration

doi:10.1109/LRA.2023.3286168

CORC > 自动化研究所 > 中国科学院自动化研究所 > 多模态人工智能系统全国重点实验室

	An Accurate Outlier Rejection Network With Higher Generalization Ability for Point Cloud Registration
	Guo, Shiyi 1,2; Tang, Fulin 2; Liu, Bingxi 3; Fu, Yujie 1,2; Wu, Yihong 1,2
刊名	IEEE ROBOTICS AND AUTOMATION LETTERS
	2023-08-01
卷号	8 期号:8 页码:4649-4656
关键词	Point cloud compression Three-dimensional displays Feature extraction Correlation Learning systems Task analysis Robustness Point cloud registration outlier rejection 3D feature
ISSN号	2377-3766
DOI	10.1109/LRA.2023.3286168
通讯作者	Wu, Yihong(yhwu@nlpr.ia.ac.cn)
英文摘要	Feature-based point cloud registration algorithms have gained more attention recently for their high robustness. Outlier rejection is a key step of such algorithms. With the development of deep learning, some of the learning-based outlier rejection methods have been proposed and implemented in various scenes. However, generalization ability and accuracy of the existing methods in complex scenes still need to be improved. In this letter, we construct a neural network for removing outlier correspondences. Particularly, we propose a novel seed selection method based on feature consistency (FC) and a new loss function based on second order feature consistency (FC$<^>{2}$). Experimental results on various datasets show the proposed network achieves better accuracy and stronger generalization ability than the state-of-the-art learning-based algorithms.
资助项目	National Natural Science Foundation of China[62202468] ; National Natural Science Foundation of China[61836015] ; National Natural Science Foundation of China[62002359]
WOS研究方向	Robotics
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:001021244900003
资助机构	National Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/53639]
专题	多模态人工智能系统全国重点实验室
通讯作者	Wu, Yihong
作者单位	1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China 3.Peng Cheng Lab, Shenzhen 518066, Peoples R China
推荐引用方式 GB/T 7714	Guo, Shiyi,Tang, Fulin,Liu, Bingxi,et al. An Accurate Outlier Rejection Network With Higher Generalization Ability for Point Cloud Registration[J]. IEEE ROBOTICS AND AUTOMATION LETTERS,2023,8(8):4649-4656.
APA	Guo, Shiyi,Tang, Fulin,Liu, Bingxi,Fu, Yujie,&Wu, Yihong.(2023).An Accurate Outlier Rejection Network With Higher Generalization Ability for Point Cloud Registration.IEEE ROBOTICS AND AUTOMATION LETTERS,8(8),4649-4656.
MLA	Guo, Shiyi,et al."An Accurate Outlier Rejection Network With Higher Generalization Ability for Point Cloud Registration".IEEE ROBOTICS AND AUTOMATION LETTERS 8.8(2023):4649-4656.