CIOMP OpenIR
Multistage Adaptive Point-Growth Network for Dense Point Cloud Completion
R. D. Hao; Z. H. Wei; X. He; K. F. Zhu; J. Wang; J. W. He and L. Zhang
2022
发表期刊Remote Sensing
卷号14期号:20页码:19
摘要The point cloud data from actual measurements are often sparse and incomplete, making it difficult to apply them directly to visual processing and 3D reconstruction. The point cloud completion task can predict missing parts based on a sparse and incomplete point cloud model. However, the disordered and unstructured characteristics of point clouds make it difficult for neural networks to obtain detailed spatial structures and topological relationships, resulting in a challenging point cloud completion task. Existing point cloud completion methods can only predict the rough geometry of the point cloud, but cannot accurately predict the local details. To address the shortcomings of existing point cloud complementation methods, this paper describes a novel network for adaptive point cloud growth, MAPGNet, which generates a sparse skeletal point cloud using the skeletal features in the composite encoder, and then adaptively grows the local point cloud in the spherical neighborhood of each point using the growth features to complement the details of the point cloud in two steps. In this paper, the Offset Transformer module is added in the process of complementation to enhance the contextual connection between point clouds. As a result, MAPGNet improves the quality of the generated point clouds and recovers more local detail information. Comparing our algorithm with other state-of-the-art algorithms in different datasets, experimental results show that our algorithm has advantages in dense point cloud completion.
DOI10.3390/rs14205214
URL查看原文
收录类别sci ; ei
语种英语
引用统计
文献类型期刊论文
条目标识符http://ir.ciomp.ac.cn/handle/181722/66886
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
R. D. Hao,Z. H. Wei,X. He,et al. Multistage Adaptive Point-Growth Network for Dense Point Cloud Completion[J]. Remote Sensing,2022,14(20):19.
APA R. D. Hao,Z. H. Wei,X. He,K. F. Zhu,J. Wang,&J. W. He and L. Zhang.(2022).Multistage Adaptive Point-Growth Network for Dense Point Cloud Completion.Remote Sensing,14(20),19.
MLA R. D. Hao,et al."Multistage Adaptive Point-Growth Network for Dense Point Cloud Completion".Remote Sensing 14.20(2022):19.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Multistage Adaptive (6706KB)期刊论文出版稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[R. D. Hao]的文章
[Z. H. Wei]的文章
[X. He]的文章
百度学术
百度学术中相似的文章
[R. D. Hao]的文章
[Z. H. Wei]的文章
[X. He]的文章
必应学术
必应学术中相似的文章
[R. D. Hao]的文章
[Z. H. Wei]的文章
[X. He]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Multistage Adaptive Point-Growth Network for D.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

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。