Deep Learning for 3D Point Cloud Understanding: A Survey

TL;DR

This survey reviews recent advances in applying deep learning techniques to 3D point cloud understanding, covering various tasks, datasets, and performance benchmarks in the context of autonomous driving and robotics.

Contribution

It provides a comprehensive summary of recent research, challenges, and progress in deep learning methods for 3D point cloud analysis across multiple tasks.

Findings

Deep learning has achieved significant progress in 3D point cloud tasks.

Various datasets and metrics are used to evaluate performance.

State-of-the-art methods show promising results in classification, segmentation, and detection.

Abstract

The development of practical applications, such as autonomous driving and robotics, has brought increasing attention to 3D point cloud understanding. While deep learning has achieved remarkable success on image-based tasks, there are many unique challenges faced by deep neural networks in processing massive, unstructured and noisy 3D points. To demonstrate the latest progress of deep learning for 3D point cloud understanding, this paper summarizes recent remarkable research contributions in this area from several different directions (classification, segmentation, detection, tracking, flow estimation, registration, augmentation and completion), together with commonly used datasets, metrics and state-of-the-art performances. More information regarding this survey can be found at: https://github.com/SHI-Labs/3D-Point-Cloud-Learning.