Extracting Cycle-aware Feature Curve Networks from 3D Models

doi:10.1016/j.cad.2020.102949

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 三维可视计算

	Extracting Cycle-aware Feature Curve Networks from 3D Models
	Lu, Zhengda 1,2; Guo, Jianwei 1,2; Xiao, Jun 2; Wang, Ying 2; Zhang, Xiaopeng 1,2; Yan, Dong-Ming 1,2
刊名	COMPUTER-AIDED DESIGN
	2021-02-01
卷号	131 页码:11
关键词	Shape analysis Feature curve network Segmentation
ISSN号	0010-4485
DOI	10.1016/j.cad.2020.102949
通讯作者	Guo, Jianwei(jianwei.guo@nlpr.ia.ac.cn) ; Xiao, Jun(xiaojun@ucas.ac.cn)
英文摘要	Meaningful feature curves provide high-level shape representation of the geometrical shapes and are useful in various applications. In this paper, we propose an automatic method on the basis of the quadric surface fitting technique to extract complete feature curve networks (FCNs) from 3D surface meshes, as well as finding cycles and generating a high-quality segmentation. In the initial collection of noisy and fragmented feature curves, we first fit the quadric surfaces of each curve and the corresponding neighbor vertices to filter out non-salient or noisy feature curves. Then we conduct a feature extension step to address the curve intersections and form a closed FCN. Finally, we regard circle curves as cycles in the complete FCN and segment the mesh into patches to reveal a highly structured representation of the input geometry. Experimental results demonstrate that our algorithm is more robust for FCN extraction from complex input meshes and achieves higher quality patch layouts compared with the state-of-the-art approaches. We also verify the validity of extracted feature curve cycles by applying them to surface reconstruction. (c) 2020 Elsevier Ltd. All rights reserved.
资助项目	National Key R&D Program, China[2018YFB2100602] ; NSFC, China[61802406] ; NSFC, China[61772523] ; Beijing science and technology project, China[Z181100003818019] ; Youth Innovation Promotion Association of CAS, China[Y201935] ; Beijing Natural Science Foundation, China[L182059] ; Open Project Program of State Key Laboratory of Virtual Reality Technology and Systems Beihang University, China[VRLAB2019B02] ; CCF-Tencent Open Research Fund, China[RAGR20190105] ; Key Research Program of Frontier Sciences CAS, China[QYZDY-SSW-SYS004]
WOS研究方向	Computer Science
语种	英语
出版者	ELSEVIER SCI LTD
WOS记录号	WOS:000596601700004
资助机构	National Key R&D Program, China ; NSFC, China ; Beijing science and technology project, China ; Youth Innovation Promotion Association of CAS, China ; Beijing Natural Science Foundation, China ; Open Project Program of State Key Laboratory of Virtual Reality Technology and Systems Beihang University, China ; CCF-Tencent Open Research Fund, China ; Key Research Program of Frontier Sciences CAS, China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/42814]
专题	模式识别国家重点实验室_三维可视计算
通讯作者	Guo, Jianwei; Xiao, Jun
作者单位	1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Lu, Zhengda,Guo, Jianwei,Xiao, Jun,et al. Extracting Cycle-aware Feature Curve Networks from 3D Models[J]. COMPUTER-AIDED DESIGN,2021,131:11.
APA	Lu, Zhengda,Guo, Jianwei,Xiao, Jun,Wang, Ying,Zhang, Xiaopeng,&Yan, Dong-Ming.(2021).Extracting Cycle-aware Feature Curve Networks from 3D Models.COMPUTER-AIDED DESIGN,131,11.
MLA	Lu, Zhengda,et al."Extracting Cycle-aware Feature Curve Networks from 3D Models".COMPUTER-AIDED DESIGN 131(2021):11.