中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
A Partial Point Cloud Completion Network Focusing on Detail Reconstruction

文献类型:期刊论文

作者M. Wei, J. Sun, Y. Zhang, M. Zhu, H. Nie, H. Liu and J. Wang
刊名Remote Sensing
出版日期2023
卷号15期号:23
ISSN号20724292
DOI10.3390/rs15235504
英文摘要The point cloud is disordered and unstructured, and it is difficult to extract detailed features. The detailed part of the target shape is difficult to complete in the point cloud completion task. It proposes a point cloud completion network (BCA-Net) focusing on detail reconstruction, which can reduce noise and refine shapes. Specifically, it utilizes residual deformation architecture to avoid error points. The break and recombine refinement method is used to recover complete point cloud details. In addition, it proposes a bilateral confidence aggregation unit based on recurrent path aggregation to refine the coarse point cloud shape using multiple gating. Our experiments on the ShapeNet and Complete3D datasets demonstrate that our network performs better than other point cloud completion networks. © 2023 by the authors.
URL标识查看原文
源URL[http://ir.ciomp.ac.cn/handle/181722/68009]  
专题中国科学院长春光学精密机械与物理研究所
推荐引用方式
GB/T 7714
M. Wei, J. Sun, Y. Zhang, M. Zhu, H. Nie, H. Liu and J. Wang. A Partial Point Cloud Completion Network Focusing on Detail Reconstruction[J]. Remote Sensing,2023,15(23).
APA M. Wei, J. Sun, Y. Zhang, M. Zhu, H. Nie, H. Liu and J. Wang.(2023).A Partial Point Cloud Completion Network Focusing on Detail Reconstruction.Remote Sensing,15(23).
MLA M. Wei, J. Sun, Y. Zhang, M. Zhu, H. Nie, H. Liu and J. Wang."A Partial Point Cloud Completion Network Focusing on Detail Reconstruction".Remote Sensing 15.23(2023).

入库方式: OAI收割

来源:长春光学精密机械与物理研究所

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。