Research on a Multi-view Point Cloud Upsampling Algorithm Based on Plane Projection.

Saved in:

Bibliographic Details
Title:	Research on a Multi-view Point Cloud Upsampling Algorithm Based on Plane Projection.
Authors:	Li, Jingying¹ lijingying2004@xupt.edu.cn, Xue, Yuhan² 740563556@qq.com, Song, Kai² 18293469338@163.com, Huang, Qiongdan³ limitless010@163.com
Source:	Engineering Letters. Jul2026, Vol. 34 Issue 7, p3047-3058. 12p.
Subjects:	Point cloud, Sampling (Process), Graphical projection, Algorithms, Interpolation, Electronic data processing
Abstract:	Conventional point cloud up-sampling methods frequently encounter challenges such as inadequate geometric feature preservation, limited robustness, and suboptimal performance when handling sparse data. To mitigate these issues, this paper proposes a novel adaptive multi-view upsampling algorithm based on plane projection. The method incorporates a pre-sampling feature extraction mechanism designed to preserve critical geometric details while ensuring interpolation integrity. Additionally, it integrates a dynamic viewpoint sampling system that allows for the adjustment of sampling density via customizable angular parameters, thereby demonstrating enhanced robustness and superior performance in sparse point cloud processing. Furthermore, a novel noise projection technique is introduced to project outlier points onto optimal tangent planes. This process effectively converts noise into valid interpolation data and improves both sampling efficiency and overall point cloud quality. [ABSTRACT FROM AUTHOR]
	Copyright of Engineering Letters is the property of International Association of Engineers (IAENG) and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Engineering Source

Description
Abstract:	Conventional point cloud up-sampling methods frequently encounter challenges such as inadequate geometric feature preservation, limited robustness, and suboptimal performance when handling sparse data. To mitigate these issues, this paper proposes a novel adaptive multi-view upsampling algorithm based on plane projection. The method incorporates a pre-sampling feature extraction mechanism designed to preserve critical geometric details while ensuring interpolation integrity. Additionally, it integrates a dynamic viewpoint sampling system that allows for the adjustment of sampling density via customizable angular parameters, thereby demonstrating enhanced robustness and superior performance in sparse point cloud processing. Furthermore, a novel noise projection technique is introduced to project outlier points onto optimal tangent planes. This process effectively converts noise into valid interpolation data and improves both sampling efficiency and overall point cloud quality. [ABSTRACT FROM AUTHOR]
ISSN:	1816093X