中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 三维可视计算
Geometry Guided Deep Surface Normal Estimation

文献类型：期刊论文

作者Zhang, Jie1; Cao, Jun-Jie2; Zhu, Hai-Rui2; Yan, Dong-Ming3,4; Liu, Xiu-Ping2
刊名COMPUTER-AIDED DESIGN
出版日期2022
卷号142页码:10
关键词Normal estimation Unstructured 3D point clouds 3D point cloud deep learning
ISSN号0010-4485
DOI10.1016/j.cad.2021.103119
通讯作者Cao, Jun-Jie(jjcao@dlut.edu.cn)
英文摘要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.
WOS关键词NORMAL VECTOR ESTIMATION ; ROBUST NORMAL ESTIMATION ; CLOUD NORMAL ESTIMATION ; POINT CLOUDS ; RECONSTRUCTION
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]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:000702862700002
出版者ELSEVIER SCI LTD
资助机构NSFC, China ; Program of Star of Dalian Youth Science and Technology, China ; National Key Research and Development Program of China
源URL[http://ir.ia.ac.cn/handle/173211/45771]  
专题模式识别国家重点实验室_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.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。