A comprehensive overview of deep learning techniques for 3D point cloud classification and semantic segmentation

Abstract

Point cloud analysis has a wide range of applications in many areas such as computer vision, robotic manipulation, and autonomous driving. While deep learning has achieved remarkable success on image-based tasks, there are many unique challenges faced by deep neural networks in processing massive, unordered, irregular and noisy 3D points. To stimulate future research, this paper analyzes recent progress in deep learning methods employed for point cloud processing and presents challenges and potential directions to advance this field. It serves as a comprehensive review on two major tasks in 3D point cloud processing-- namely, 3D shape classification and semantic segmentation.

Published in Springer Nature (Machine Vision and Applications)

References in corpus (17)

• Res2Net: A New Multi-scale Backbone Architecture
• PCT: Point cloud transformer
• Rotational Projection Statistics for 3D Local Surface Description and Object Recognition
• Linking Points With Labels in 3D: A Review of Point Cloud Semantic Segmentation
• Deep Parametric Continuous Convolutional Neural Networks
• Toronto-3D: A Large-scale Mobile LiDAR Dataset for Semantic Segmentation of Urban Roadways
• Point Transformer
• Exploring Spatial Context for 3D Semantic Segmentation of Point Clouds
• Monte Carlo Convolution for Learning on Non-Uniformly Sampled Point Clouds
• PRA-Net: Point Relation-Aware Network for 3D Point Cloud Analysis
• PointHop: An Explainable Machine Learning Method for Point Cloud Classification
• FPS-Net: A Convolutional Fusion Network for Large-Scale LiDAR Point Cloud Segmentation
• Campus3D: A Photogrammetry Point Cloud Benchmark for Hierarchical Understanding of Outdoor Scene
• Meta-RangeSeg: LiDAR Sequence Semantic Segmentation Using Multiple Feature Aggregation
• DeltaConv: Anisotropic Operators for Geometric Deep Learning on Point Clouds
• PIG-Net: Inception based Deep Learning Architecture for 3D Point Cloud Segmentation
• PointSCNet: Point Cloud Structure and Correlation Learning Based on Space Filling Curve-Guided Sampling

Cited by in corpus (3)

• A Deep Learning Approach to Identify Rock Bolts in Complex 3D Point Clouds of Underground Mines Captured Using Mobile Laser Scanners
• Graph-Guided Dual-Level Augmentation for 3D Scene Segmentation
• SemanticBridge - A Dataset for 3D Semantic Segmentation of Bridges and Domain Gap Analysis