%0 Journal Article
%T 基于深度学习的点云上采样算法研究<br>Research on Point Cloud Upsampling Algorithms Based on Deep Learning
%A 王皓辰
%A 张长伦
%A 黎铭亮
%J Journal of Image and Signal Processing
%P 21-31
%@ 2325-6745
%D 2023
%I Hans Publishing
%R 10.12677/JISP.2023.121003
%X 点云上采样能够提高点云分辨率并保持点云的特征，近年来越来越受到人们的重视。基于深度学习的点云上采样算法相较于基于优化的算法，能够更有效地学习点云的特征和结构，且对数据的先验要求不高，取得了先进的上采样效果。因此基于深度学习的点云上采样是当前许多学者主要研究的方向之一。本文综述了基于深度学习的点云上采样算法，阐述了点云上采样的整体框架以及改进的策略，并介绍了点云上采样效果的评价指标以及常用的数据集，最后探讨了点云上采样的未来的几个极具潜力的发展方向。<br />
Point cloud upsampling improves the resolution of point cloud and maintains the feature of point cloud, which has attracted more and more attention in recent years. Compared with the optimization-based algorithms, the point cloud upsampling algorithms based on deep learning can more effectively learn the feature and structure of the point cloud and have low prior requirements for data, leading to the advanced effect of upsampling. Therefore, the point cloud upsampling based on deep learning is one of the main research directions of many scholars at present. In this paper, we summarize the point cloud upsampling algorithms based on deep learning and expound the holistic framework and improved strategies of point cloud upsampling. Then the evaluation metrics of point cloud upsampling effect and commonly used data sets are introduced. We finally discuss several potential development directions of point cloud upsampling in the future.
%K 深度学习，点云上采样<br>Deep Learning
%K Point Cloud Upsampling
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=60138