3DTDesc: learning local features using 2D and 3D cues

doi:10.1007/s00138-021-01176-8

CORC > 自动化研究所 > 中国科学院自动化研究所 > 综合信息系统研究中心 > 视知觉融合及其应用

	3DTDesc: learning local features using 2D and 3D cues
	Xing, Xiaoxia 2,3; Cai, Yinghao 3; Lu, Tao 1; Yang, Yiping 3; Wen, Dayong 3
刊名	MACHINE VISION AND APPLICATIONS
	2021-05-01
卷号	32 期号:3 页码:15
关键词	Geometric feature Texture feature Fusion method Registration
ISSN号	0932-8092
DOI	10.1007/s00138-021-01176-8
通讯作者	Xing, Xiaoxia(xingxiaoxia2015@ia.ac.cn)
英文摘要	Pairwise frame registration with sparse geometric local features on real-world depth images is not particularly robust due to the low resolution and incomplete nature of the 3D scan data. Moreover, there might be many regions with similar geometric information. In this paper, we present 3DTDesc, a data-driven descriptor which closely combines both 2D texture and 3D geometric information for frame registration. The proposed descriptor is learned directly from color point clouds, which is time-efficient and provides robust and accurate geometric feature matching in a variety of settings. The texture information and the geometric information closely interact in the fusing network, which are complements of each other in situations of textureless regions or regions with similar geometric information and different texture information. We also propose a multi-scale 3DTDesc to further improve the performance of the feature matching. The effectiveness and efficiency of our proposed 3DTDesc are demonstrated by extensive experimental results on challenging RGB-D datasets and various ablation studies.
资助项目	National Natural Science Foundation of China[U1913201]
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	SPRINGER
WOS记录号	WOS:000625119800001
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/173211/43311]
专题	综合信息系统研究中心_视知觉融合及其应用
通讯作者	Xing, Xiaoxia
作者单位	1.Univ Chinese Acad Sci, Inst Automat, 95 Zhongguancun East Rd, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China 3.Univ Chinese Acad Sci, Inst Automat, 95 Zhongguancun East Rd, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Xing, Xiaoxia,Cai, Yinghao,Lu, Tao,et al. 3DTDesc: learning local features using 2D and 3D cues[J]. MACHINE VISION AND APPLICATIONS,2021,32(3):15.
APA	Xing, Xiaoxia,Cai, Yinghao,Lu, Tao,Yang, Yiping,&Wen, Dayong.(2021).3DTDesc: learning local features using 2D and 3D cues.MACHINE VISION AND APPLICATIONS,32(3),15.
MLA	Xing, Xiaoxia,et al."3DTDesc: learning local features using 2D and 3D cues".MACHINE VISION AND APPLICATIONS 32.3(2021):15.