Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Survey

Authors

Aoran Xiao, School of Computer Science and Engineering
Jiaxing Huang, School of Computer Science and Engineering
Dayan Guan, Mohamed Bin Zayed University of Artificial IntelligenceFollow
Xiaoqin Zhang, Wenzhou University
Shijian Lu, School of Computer Science and Engineering
Ling Shao, University of Chinese Academy of Sciences

Document Type

Article

Publication Title

IEEE Transactions on Pattern Analysis and Machine Intelligence

Abstract

Point cloud data have been widely explored due to its superior accuracy and robustness under various adverse situations. Meanwhile, deep neural networks (DNNs) have achieved very impressive success in various applications such as surveillance and autonomous driving. The convergence of point cloud and DNNs has led to many deep point cloud models, largely trained under the supervision of large-scale and densely-labelled point cloud data. Unsupervised point cloud representation learning, which aims to learn general and useful point cloud representations from unlabelled point cloud data, has recently attracted increasing attention due to the constraint in large-scale point cloud labelling. This paper provides a comprehensive review of unsupervised point cloud representation learning using DNNs. It first describes the motivation, general pipelines as well as terminologies of the recent studies. Relevant background including widely adopted point cloud datasets and DNN architectures is then briefly presented. This is followed by an extensive discussion of existing unsupervised point cloud representation learning methods according to their technical approaches. We also quantitatively benchmark and discuss the reviewed methods over multiple widely adopted point cloud datasets. Finally, we share our humble opinion about several challenges and problems that could be pursued in the future research in unsupervised point cloud representation learning. A project associated with this survey has been built at https://github.com/xiaoaoran/3d url survey.

First Page

1

Last Page

20

DOI

10.1109/TPAMI.2023.3262786

Publication Date

3-29-2023

Keywords

3D vision, deep learning, Deep learning, deep neural network, Point cloud, Point cloud compression, pre-training, Representation learning, self-supervised learning, Semantic segmentation, Task analysis, Three-dimensional displays, transfer learning, Uniform resource locators, unsupervised representation learning

Comments

IR Deposit conditions:

OA version (pathway a) Accepted version

No embargo

When accepted for publication, set statement to accompany deposit (see policy)

Must link to publisher version with DOI

Publisher copyright and source must be acknowledged

Recommended Citation

A. Xiao, J. Huang, D. Guan, X. Zhang, S. Lu and L. Shao, "Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Survey," in IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 1-20, March 2023, doi: 10.1109/TPAMI.2023.3262786.