Deep Learning for 3D Point Clouds: A Survey

TL;DR

This survey reviews recent deep learning methods for 3D point clouds, covering tasks like shape classification, detection, and segmentation, highlighting progress, challenges, and future research directions.

Contribution

It provides a comprehensive overview of recent advances in deep learning for point clouds, including comparative results and insights to guide future research.

Findings

Deep learning has shown significant progress in 3D shape classification.

Various methods have been developed for object detection and segmentation in point clouds.

The survey identifies key challenges and promising directions for future research.

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.