大规模室外图像3维重建技术研究进展  

Progress in the large-scale outdoor image 3D reconstruction

作　　者：颜深 张茂军[1] 樊亚春[2] 谭小慧[3] 刘煜 彭杨 刘宇翔 Yan Shen;Zhang Maojun;Fan Yachun;Tan Xiaohui;Liu Yu;Peng Yang;Liu Yuxiang(School of System Engineering,National University of Defense Technology,Changsha 410073,China;School of Artificial Intelligence,Beijing Normal University,Beijing 100875,China;Information Engineering College,Capital Normal University,Beijing 100048,China)

机构地区：[1]国防科技大学系统工程学院,长沙410073 [2]北京师范大学人工智能学院,北京100875 [3]首都师范大学信息工程学院,北京100048

出　　处：《中国图象图形学报》2021年第6期1429-1449,共21页Journal of Image and Graphics

基　　金：国家自然科学基金项目(61906206,61703415,62071478);湖南省自然科学基金项目(2019JJ50746)。

摘　　要：基于图像的3维重建旨在从一组2维多视角图像中精确地恢复真实场景的几何形状,是计算机视觉和摄影测量中基础且活跃的研究课题,具有重要的理论研究意义和应用价值,在智慧城市、虚拟旅游、数字遗产保护、数字地图和导航等领域有着广泛应用。随着图像采集系统(智能手机、消费级数码相机和民用无人机等)的普及和互联网的高速发展,通过搜索引擎可以获取大量关于某个室外场景的互联网图像。利用这些图像进行高效鲁棒准确的3维重建,为用户提供真实感知和沉浸式体验已经成为研究热点,引发了学术界和产业界的广泛关注,涌现了多种方法。深度学习的出现为大规模室外图像的3维重建提供了新的契机。首先阐述大规模室外图像3维重建的基本串行过程,包括图像检索、图像特征点匹配、运动恢复结构和多视图立体。然后从传统方法和基于深度学习的方法两个角度,分别系统全面地回顾大规模室外图像3维重建技术在各重建子过程中的发展和应用,总结各子过程中适用于大规模室外场景的数据集和评价指标。最后介绍现有主流的开源和商业3维重建系统以及国内相关产业的发展现状。3 D reconstruction aims to accurately restore the geometry of an actual scene.It is a fundamental and active research field in computer vision and photogrammetry with important theoretical significance and application value.Acquisition of 3 D models is highly relevant for various applications,including smart city,virtual tourism,digital heritage preservation,mapping,and navigation.Various technologies that enable 3 D modeling have been developed,and each of them has its own benefits and drawbacks for certain applications.The methods can be classified into two categories,namely,active acquisition methods(e.g.,LiDAR and radar)and passive ones(i.e.,cameras).As a passive acquisition method,cameras are especially power efficient and do not need direct physical contact with the actual world,and 3 D model can be effectively rebuilt from a set of 2 D multiview images.In addition,with the increasing availability of cameras as commodity sensors in consumer devices,the cost of camera hardware has decreased significantly.Over the last decades,with the popularization of image acquisition systems(including smart phones,consumer-grade digital cameras,and civil drones)and the rapid development of the Internet,normal people can easily obtain a large number of Internet images about an outdoor scene through search engines(such as Google,Bing,or Baidu).Organizing and utilizing these extremely rich and diverse data source to perform efficient,robust,and accurate 3 D reconstruction to provide users with actual perception and immersive experience have become a research hotspot and have attracted widespread attention from the academic and industrial circles.For a human,building an accurate and complete 3 D representation of the actual world on the fly is natural,but abstracting the underlying problem in a computer program is extremely hard.Nowadays,many of the underlying problems in large-scale outdoor 3 D reconstruction are gradually understood,but many problems,which the research community has not deeply understood,still exist.3 D mod

关 键 词：3维重建 图像检索 图像特征点匹配 运动恢复结构 多视图立体 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]