Geometry Guided Deep Surface Normal Estimation

doi:10.1016/j.cad.2021.103119

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

	Geometry Guided Deep Surface Normal Estimation
	Zhang, Jie 1; Cao, Jun-Jie 2; Zhu, Hai-Rui 2; Yan, Dong-Ming3,4 ; Liu, Xiu-Ping 2
发表期刊	COMPUTER-AIDED DESIGN
ISSN	0010-4485
	2022
卷号	142 页码:10
通讯作者	Cao, Jun-Jie(jjcao@dlut.edu.cn)
摘要	We propose a geometry-guided neural network architecture for robust and detail-preserving surface normal estimation for unstructured point clouds. Previous deep normal estimators usually estimate the normal directly from the neighbors of a query point, which lead to poor performance. The proposed network is composed of a weight learning sub-network (WL-Net) and a lightweight normal learning sub-network (NL-Net). WL-Net first predicates point-wise weights for generating an optimized point set (OPS) from the input. Then, NL-Net estimates a more accurate normal from the OPS especially when the local geometry is complex. To boost the weight learning ability of the WL-Net, we introduce two geometric guidance in the network. First, we design a weight guidance using the deviations between the neighbor points and the ground truth tangent plane of the query point. This deviation guidance offers a "ground truth" for weights corresponding to some reliable inliers and outliers determined by the tangent plane. Second, we integrate the normals of multiple scales into the input. Its performance and robustness are further improved without relying on multi-branch networks, which are employed in previous multi-scale normal estimators. Thus our method is more efficient. Qualitative and quantitative evaluations demonstrate the advantages of our approach over the state-of-the-art methods, in terms of estimation accuracy, model size and inference time. Code is available at https://github.com/2429581027/local-geometric-guided. (C) 2021 Elsevier Ltd. All rights reserved.
关键词	Normal estimation Unstructured 3D point clouds 3D point cloud deep learning
DOI	10.1016/j.cad.2021.103119
关键词[WOS]	NORMAL VECTOR ESTIMATION ; ROBUST NORMAL ESTIMATION ; CLOUD NORMAL ESTIMATION ; POINT CLOUDS ; RECONSTRUCTION
收录类别	SCI
语种	英语
资助项目	NSFC, China[61976040] ; NSFC, China[62076115] ; NSFC, China[61702245] ; NSFC, China[61976041] ; NSFC, China[61772104] ; NSFC, China[62172415] ; Program of Star of Dalian Youth Science and Technology, China[2020RQ053] ; National Key Research and Development Program of China[2020YFB1708900]
项目资助者	NSFC, China ; Program of Star of Dalian Youth Science and Technology, China ; National Key Research and Development Program of China
WOS研究方向	Computer Science
WOS类目	Computer Science, Software Engineering
WOS记录号	WOS:000702862700002
出版者	ELSEVIER SCI LTD
引用统计	被引频次：12[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/173211/45772
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	Cao, Jun-Jie
作者单位	1.Liaoning Normal Univ, Sch Math, Dalian 116024, Liaoning, Peoples R China 2.Dalian Univ Technol, Sch Math Sci, Dalian 116029, Liaoning, Peoples R China 3.Chinese Acad Sci, Inst Automat, NLPR, Beijing 100190, Peoples R China 4.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Jie,Cao, Jun-Jie,Zhu, Hai-Rui,et al. Geometry Guided Deep Surface Normal Estimation[J]. COMPUTER-AIDED DESIGN,2022,142:10.
APA	Zhang, Jie,Cao, Jun-Jie,Zhu, Hai-Rui,Yan, Dong-Ming,&Liu, Xiu-Ping.(2022).Geometry Guided Deep Surface Normal Estimation.COMPUTER-AIDED DESIGN,142,10.
MLA	Zhang, Jie,et al."Geometry Guided Deep Surface Normal Estimation".COMPUTER-AIDED DESIGN 142(2022):10.