%0 Journal Article
%T 点云上采样技术研究<br>Research on Point Cloud Upsampling Technologies
%A 徐天
%A 张长伦
%J Journal of Image and Signal Processing
%P 10-20
%@ 2325-6745
%D 2024
%I Hans Publishing
%R 10.12677/JISP.2024.131002
%X 点云上采样旨在将稀疏、嘈杂、不完整的点云转换为密集、干净、完整的点云，这样有利于提高下游任务的性能。当前的点云上采样方法主要分为基于优化和基于学习的方法，本文针对基于深度学习的点云上采样算法进行了综述。本文从点云上采样的开山之作PU-Net引入，阐述了上采样算法的发展，并总结了插值算法在点云上采样中的应用，然后对不同特征扩展方法进行了比较，介绍了上采样算法的评价指标和常用数据集，最后对点云上采样的发展前景进行了展望。<br />
Point cloud upsampling aims to convert sparse, noisy, and incomplete point clouds into dense, clean, and complete point clouds, which is conducive to improving the performance of downstream tasks. Current point cloud upsampling algorithms are mainly classified into optimization-based and learning-based methods, and this paper provides a review of deep learning-based point cloud up-sampling algorithms. This paper introduces PU-Net, the pioneer of point cloud upsampling. Then it describes the development of upsampling algorithms and summarizes the application of interpolation algorithms in point cloud upsampling. Then it compares the different feature expansion meth-ods, introduces the evaluation indexes of upsampling algorithms and the commonly used datasets. Finally, it looks forward to the development prospects of point cloud upsampling.
%K 深度学习，点云上采样，特征扩展<br>Deep Learning
%K Point Cloud Upsampling
%K Feature Expansion
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=79245