Deep Learning for 3D Point Clouds: A Survey

Yulan Guo, Hanyun Wang, Qingyong Hu, Hao Liu, Li Liu, Mohammed Bennamoun

Research output: Contribution to journalReview articlepeer-review

415 Citations (Web of Science)

Abstract

Point cloud learning has lately attracted increasing attention due to its wide applications in many areas, such as computer vision, autonomous driving, and robotics. As a dominating technique in AI, deep learning has been successfully used to solve various 2D vision problems. However, deep learning on point clouds is still in its infancy due to the unique challenges faced by the processing of point clouds with deep neural networks. Recently, deep learning on point clouds has become even thriving, with numerous methods being proposed to address different problems in this area. To stimulate future research, this paper presents a comprehensive review of recent progress in deep learning methods for point clouds. It covers three major tasks, including 3D shape classification, 3D object detection and tracking, and 3D point cloud segmentation. It also presents comparative results on several publicly available datasets, together with insightful observations and inspiring future research directions.

Original languageEnglish
Pages (from-to)4338-4364
Number of pages27
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume43
Issue number12
DOIs
Publication statusPublished - 1 Dec 2021

Fingerprint

Dive into the research topics of 'Deep Learning for 3D Point Clouds: A Survey'. Together they form a unique fingerprint.

Cite this