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
Accurate Registration of Cross-Modality Geometry via Consistent Clustering

文献类型：期刊论文

作者Zhao, Mingyang1,2; Huang, Xiaoshui3; Jiang, Jingen2,4,5; Mou, Luntian6; Yan, Dong-Ming2,4,5; Ma, Lei7,8,9
刊名IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
出版日期2024-07-01
卷号30期号:7页码:4055-4067
关键词Point cloud compression Geometry Three-dimensional displays Laser radar Tensors Clustering algorithms Solid modeling Cross-modality geometry point cloud registration 3D reconstruction adaptive fuzzy clustering CAD
ISSN号1077-2626
DOI10.1109/TVCG.2023.3247169
通讯作者Yan, Dong-Ming(yandongming@gmail.com) ; Ma, Lei(lei.ma@pku.edu.cn)
英文摘要The registration of unitary-modality geometric data has been successfully explored over past decades. However, existing approaches typically struggle to handle cross-modality data due to the intrinsic difference between different models. To address this problem, in this article, we formulate the cross-modality registration problem as a consistent clustering process. First, we study the structure similarity between different modalities based on an adaptive fuzzy shape clustering, from which a coarse alignment is successfully operated. Then, we optimize the result using fuzzy clustering consistently, in which the source and target models are formulated as clustering memberships and centroids, respectively. This optimization casts new insight into point set registration, and substantially improves the robustness against outliers. Additionally, we investigate the effect of fuzzier in fuzzy clustering on the cross-modality registration problem, from which we theoretically prove that the classical Iterative Closest Point (ICP) algorithm is a special case of our newly defined objective function. Comprehensive experiments and analysis are conducted on both synthetic and real-world cross-modality datasets. Qualitative and quantitative results demonstrate that our method outperforms state-of-the-art approaches with higher accuracy and robustness. Our code is publicly available at https://github.com/zikai1/CrossModReg.
WOS关键词ITERATIVE CLOSEST POINT ; ICP
资助项目National Key R&D Program of China[2022ZD0116305] ; National Natural Science Foundation of China[62172415] ; Open Research Fund Program of State Key Laboratory of Hydroscience and Engineering, Tsinghua University[klhse-2022-D-04]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:001258936700043
出版者IEEE COMPUTER SOC
资助机构National Key R&D Program of China ; National Natural Science Foundation of China ; Open Research Fund Program of State Key Laboratory of Hydroscience and Engineering, Tsinghua University
源URL[http://ir.ia.ac.cn/handle/173211/59242]  
专题模式识别国家重点实验室_三维可视计算
通讯作者Yan, Dong-Ming; Ma, Lei
作者单位1.Chinese Acad Sci, Beijing Acad Artificial Intelligence, Inst Automat, Beijing 100045, Peoples R China
2.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100045, Peoples R China
3.Shanghai AI Lab, Shanghai 200433, Peoples R China
4.Chinese Acad Sci, State Key Lab Multimodal Artificial Intelligence, Inst Automat, Beijing 100045, Peoples R China
5.Univ Chinese Acad Sci, Sch AI, Beijing 101408, Peoples R China
6.Beijing Univ Technol, Beijing Inst Artificial Intelligence, Beijing Key Lab Multimedia & Intelligent Software, Beijing 100021, Peoples R China
7.Peking Univ, Natl Biomed Imaging Ctr, Beijing 100871, Peoples R China
8.Peking Univ, Sch Comp Sci, Beijing Acad Artificial Intelligence, Beijing 100871, Peoples R China
9.Peking Univ, Sch Comp Sci, Natl Key Lab Multimedia Informat Proc, Beijing 100871, Peoples R China
推荐引用方式
GB/T 7714		 Zhao, Mingyang,Huang, Xiaoshui,Jiang, Jingen,et al. Accurate Registration of Cross-Modality Geometry via Consistent Clustering[J]. IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS,2024,30(7):4055-4067.
APA Zhao, Mingyang,Huang, Xiaoshui,Jiang, Jingen,Mou, Luntian,Yan, Dong-Ming,&Ma, Lei.(2024).Accurate Registration of Cross-Modality Geometry via Consistent Clustering.IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS,30(7),4055-4067.
MLA Zhao, Mingyang,et al."Accurate Registration of Cross-Modality Geometry via Consistent Clustering".IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS 30.7(2024):4055-4067.

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。