三维点云数据超分辨率技术  

Overview of 3D point cloud super-resolution technology

作　　者：毕勇[1] 潘鸣奇 张硕 高伟男[1] BI Yong;PAN Ming-qi;ZHANG Shuo;GAO Wei-nan(Technical Institute of Physics and Chemistry,Chinese Academy of Sciences,Beijing 100190,China;University of Chinese Academy of Sciences,Beijing 100049,China)

机构地区：[1]中国科学院理化技术研究所,北京100190 [2]中国科学院大学,北京100049

出　　处：《中国光学》2022年第2期210-223,共14页Chinese Optics

基　　金：2020年北京市落实中央引导地方科技发展专项(No.Z20111000430000)。

摘　　要：随着机器视觉技术的发展,如何准确、高效地对真实世界进行精确记录与建模已成为热点问题。由于硬件条件的限制,通常采集到的点云数据分辨率较低,无法满足实际应用需求,因此有必要对点云数据超分辨率技术进行研究。本文介绍三维点云数据超分辨率技术的意义、进展及评价方法,并对经典超分辨率算法和基于机器学习的超分辨率算法分别进行梳理,总结了目前方法的特点,指出了目前点云数据超分辨率技术中存在的主要问题及面临的挑战,最后展望了点云数据超分辨率技术的发展方向。With the development of the computer vision technology,research on recording and modeling the real world accurately and efficiently has become a key issue.Due to the limitation of hardware,the resolu-tion of a point cloud is usually low,which cannot meet the applications.Therefore,it is necessary to study the super-resolution technology of point clouds.In this paper,we sort out the significance,progress,and evalu-ation methods of 3D point cloud super-resolution technology,introduce the classical super-resolution al-gorithm and the super-resolution algorithm based on machine learning,summarize the characteristics of the current methods,and point out the main problems and challenges in current point cloud data super-resolution technology.Finally,the future direction in point cloud super-resolution technology is proposed.

关 键 词：点云数据 点云上采样 超分辨率 机器学习 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]