3D Point Cloud Restoration via Deep Learning: A Comprehensive Survey

被引：0
作者：
Liu C. [1 ]
Wei M. [2 ]
Guo Y. [3 ]
机构：
[1] Institute of EduInfo Science & Engineering, Nanjing Normal University, Nanjing
[2] College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing
[3] State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing
来源：
Wei, Mingqiang (mqwei@nuaa.edu.cn) | 1936年 / Institute of Computing Technology卷 / 33期
关键词：
3D point cloud; Deep learning; Feature coding; Network module; Point cloud restoration;
D O I：
10.3724/SP.J.1089.2021.18817
中图分类号：
学科分类号：
摘要：
3D point cloud is one of the most commonly used 3D scene/object representation methods. According to the dif-ferent emphases of point cloud restoration, 3D point cloud restoration technologies based on deep learning are divided into three classes: dense reconstruction, complete reconstruction and denoising reconstruction. Typical restoration models and key techniques, such as feature coding, feature extension, and loss function design, are analyzed. Commonly used network modules, point cloud data sets, and evaluation criteria are summarized. Finally, the relationship between the three kinds of point cloud restoration technologies is discussed, and the challenges and future development trends of point cloud restoration technologies are explored from five aspects: rotation invariant feature extraction, detail information repair, topological relationship preservation, geometric algorithm application, and multimodal data fusion. © 2021, Beijing China Science Journal Publishing Co. Ltd. All right reserved.
引用
收藏
页码：1936 / 1952
页数：16
相关论文
共 77 条
[1]  
Pfister H, Gross M., Point-based computer graphics, IEEE Computer Graphics and Applications, 24, 4, pp. 22-23, (2004)
[2]  
Kobbelt L, Botsch M., A survey of point-based techniques in computer graphics, Computers & Graphics, 28, 6, pp. 801-814, (2004)
[3]  
Rusu R B, Cousins S., 3D is here: point cloud library (PCL), Proceedings of the IEEE International Conference on Robotics and Automation, pp. 1-4, (2011)
[4]  
Aldoma A, Marton Z C, Tombari F, Et al., Tutorial: point cloud library: three-dimensional object recognition and 6 DOF pose estimation, IEEE Robotics & Automation Magazine, 19, 3, pp. 80-91, (2012)
[5]  
Saval-Calvo M, Orts-Escolano S, Azorin-Lopez J, Et al., A comparative study of downsampling techniques for non-rigid point set registration using color, Proceedings of the International Work-conference on the Interplay Between Natural and Artificial Computation, pp. 281-290, (2015)
[6]  
Xu Z H, Wu L X, Shen Y L, Et al., Tridimensional reconstruction applied to cultural heritage with the use of camera-equipped UAV and terrestrial laser scanner, Remote Sensing, 6, 11, pp. 10413-10434, (2014)
[7]  
Chen X Z, Ma H M, Wan J, Et al., Multi-view 3D object detection network for autonomous driving, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1907-1915, (2017)
[8]  
Varley J, DeChant C, Richardson A, Et al., Shape completion enabled robotic grasping, Proceedings of the IEEE International Conference on Intelligent Robots and Systems, pp. 2442-2447, (2017)
[9]  
Berger M, Tagliasacchi A, Seversky L, Et al., State of the art in surface reconstruction from point clouds, Proceedings of Eurographics 2014-State of the Art Reports, pp. 161-185, (2014)
[10]  
Yuan W T, Khot T, Held D, Et al., PCN: point completion network, Proceedings of the International Conference on 3D Vision, pp. 728-737, (2018)
12345678