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
PuzzleNet: Boundary-Aware Feature Matching for Non-Overlapping 3D Point Clouds Assembly

文献类型：期刊论文

作者Liu, Hao-Yu1,2; Guo, Jian-Wei1,2; Jiang, Hai-Yong1; Liu, Yan-Chao1,2; Zhang, Xiao-Peng1,2; Yan, Dong-Ming1,2
刊名JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY
出版日期2023-06-01
卷号38期号:3页码:492-509
关键词shape assembly 3D registration geometric learning boundary feature point cloud
ISSN号1000-9000
DOI10.1007/s11390-023-3127-8
通讯作者Guo, Jian-Wei(jianwei.guo@nlpr.ia.ac.cn)
英文摘要We address the 3D shape assembly of multiple geometric pieces without overlaps, a scenario often encountered in 3D shape design, field archeology, and robotics. Existing methods depend on strong assumptions on the number of shape pieces and coherent geometry or semantics of shape pieces. Despite raising attention to 3D registration with complex or low overlapping patterns, few methods consider shape assembly with rare overlaps. To address this problem, we present a novel framework inspired by solving puzzles, named PuzzleNet, which conducts multi-task learning by leveraging both 3D alignment and boundary information. Specifically, we design an end-to-end neural network based on a point cloud transformer with two-way branches for estimating rigid transformation and predicting boundaries simultaneously. The framework is then naturally extended to reassemble multiple pieces into a full shape by using an iterative greedy approach based on the distance between each pair of candidate-matched pieces. To train and evaluate PuzzleNet, we construct two datasets, named DublinPuzzle and ModelPuzzle, based on a real-world urban scan dataset (DublinCity) and a synthetic CAD dataset (ModelNet40) respectively. Experiments demonstrate our effectiveness in solving 3D shape assembly for multiple pieces with arbitrary geometry and inconsistent semantics. Our method surpasses state-of-the-art algorithms by more than 10 times in rotation metrics and four times in translation metrics.
WOS关键词REGISTRATION
资助项目National Natural Science Foundation of China[62172416] ; National Natural Science Foundation of China[U21A20515] ; National Natural Science Foundation of China[62172415] ; National Natural Science Foundation of China[62271467] ; National Natural Science Foundation of China[2022131] ; Youth Innovation Promotion Association of the Chinese Academy of Sciences[U22B2034]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:001089311400003
出版者SPRINGER SINGAPORE PTE LTD
资助机构National Natural Science Foundation of China ; Youth Innovation Promotion Association of the Chinese Academy of Sciences
源URL[http://ir.ia.ac.cn/handle/173211/54457]  
专题多模态人工智能系统全国重点实验室
通讯作者Guo, Jian-Wei
作者单位1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
2.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Liu, Hao-Yu,Guo, Jian-Wei,Jiang, Hai-Yong,et al. PuzzleNet: Boundary-Aware Feature Matching for Non-Overlapping 3D Point Clouds Assembly[J]. JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY,2023,38(3):492-509.
APA Liu, Hao-Yu,Guo, Jian-Wei,Jiang, Hai-Yong,Liu, Yan-Chao,Zhang, Xiao-Peng,&Yan, Dong-Ming.(2023).PuzzleNet: Boundary-Aware Feature Matching for Non-Overlapping 3D Point Clouds Assembly.JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY,38(3),492-509.
MLA Liu, Hao-Yu,et al."PuzzleNet: Boundary-Aware Feature Matching for Non-Overlapping 3D Point Clouds Assembly".JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY 38.3(2023):492-509.

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。