Linking Points With Labels in 3D: A Review of Point Cloud Semantic Segmentation

TL;DR

This review paper summarizes recent advances in 3D point cloud semantic segmentation, covering techniques, benchmarks, and open challenges, highlighting the growing importance of deep learning in this field.

Contribution

It provides an up-to-date comprehensive overview of traditional and advanced PCSS methods, benchmarks, and key issues, serving as a valuable resource for researchers.

Findings

Comparison of traditional and deep learning techniques

Summary of existing benchmarks for PCSS

Discussion of open challenges and future directions

Abstract

3D Point Cloud Semantic Segmentation (PCSS) is attracting increasing interest, due to its applicability in remote sensing, computer vision and robotics, and due to the new possibilities offered by deep learning techniques. In order to provide a needed up-to-date review of recent developments in PCSS, this article summarizes existing studies on this topic. Firstly, we outline the acquisition and evolution of the 3D point cloud from the perspective of remote sensing and computer vision, as well as the published benchmarks for PCSS studies. Then, traditional and advanced techniques used for Point Cloud Segmentation (PCS) and PCSS are reviewed and compared. Finally, important issues and open questions in PCSS studies are discussed.