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. 力学研究所
  3. 中国科学院力学研究所
  4. 流固耦合系统力学重点实验室(2012-)
Multi-Dimensional Graph Interactional Network for Progressive Point Cloud Completion

文献类型：期刊论文

作者Xiao, Haihong4; Xu, Hongbin4; Li, Yuqiong1; Kang, Wenxiong2,3,4
刊名IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
出版日期2023
卷号72页码:12
ISSN号0018-9456
关键词Point cloud compression Shape Three-dimensional displays Decoding Rendering (computer graphics) Feature extraction Deep learning 3-D point cloud deep learning differentiable rendering multidimensional graph interactional network point cloud completion
DOI10.1109/TIM.2022.3227994
通讯作者Li, Yuqiong(liyuqiong@imech.ac.cn) ; Kang, Wenxiong(auwxkang@scut.edu.cn)
英文摘要Point cloud completion refers to inferring the complete and visually plausible shape from a partial input. Existing point cloud completion methods focus on recovering the global integrity of partial point clouds but lack local structural details. Furthermore, they seldom consider the shape faithfulness of completed results, that some completed points fail to fall into the ground-truth position faithfully. To meet the above challenges, we present a multidimensional graph interactional network for progressive point cloud completion. Specifically, we propose a multiresolution multidimensional graph encoder (MRMD-GE) to capture the information from both within-dimension and cross-dimension interactions for the purpose of enhancing the perception of local geometry. Inspired by the FPN, we develop a recursive point cloud pyramid decoder (RPPD) for generating multistage completed point clouds progressively, which incorporates extra feedback connections into the bottom-up backbone layers. In addition, we design a depth map discriminator combined with differentiable rendering to match the distribution of generated and real point clouds, making the completed point clouds more faithful to the ground truth. Quantitative and qualitative experiments on Completion3D, Shapenet-Part, and KITTI datasets demonstrate that our proposed method has compelling advantages over the state-of-the-art methods.
资助项目Youth Innovation Promotion Associationof the Chinese Academy of Sciences[2018024] ; National Natural Science Foundation of China[61976095] ; National Natural Science Foundation of China[61575209] ; Experiments for Space Exploration Pro-gram ; Qian Xuesen Laboratory ; China Academy of Space Technology[TKTSPY-2020-05-01]
WOS研究方向Engineering ; Instruments & Instrumentation
语种英语
WOS记录号WOS:000915866600046
资助机构Youth Innovation Promotion Associationof the Chinese Academy of Sciences ; National Natural Science Foundation of China ; Experiments for Space Exploration Pro-gram ; Qian Xuesen Laboratory ; China Academy of Space Technology
源URL[http://dspace.imech.ac.cn/handle/311007/92917]  
专题力学研究所_流固耦合系统力学重点实验室(2012-)
通讯作者Li, Yuqiong; Kang, Wenxiong
作者单位1.Chinese Acad Sci, Inst Mech, Key Lab Mech Fluid Solid Coupling Syst, Beijing 100190, Peoples R China
2.Pazhou Lab, Young Scholar Project Ctr, Guangzhou 510335, Peoples R China
3.South China Univ Technol, Sch Future Technol, Guangzhou, Peoples R China
4.South China Univ Technol, Sch Automat Sci & Engn, Guangzhou 511442, Peoples R China
推荐引用方式
GB/T 7714		 Xiao, Haihong,Xu, Hongbin,Li, Yuqiong,et al. Multi-Dimensional Graph Interactional Network for Progressive Point Cloud Completion[J]. IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT,2023,72:12.
APA Xiao, Haihong,Xu, Hongbin,Li, Yuqiong,&Kang, Wenxiong.(2023).Multi-Dimensional Graph Interactional Network for Progressive Point Cloud Completion.IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT,72,12.
MLA Xiao, Haihong,et al."Multi-Dimensional Graph Interactional Network for Progressive Point Cloud Completion".IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 72(2023):12.

入库方式： OAI收割

来源：力学研究所

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。