Analysis of Current Advancement in 3D Point Cloud Semantic Segmentation

Abstract

INTRODUCTION: The division of a 3D point cloud into various meaningful regions or objects is known as point cloud segmentation. OBJECTIVES: The paper discusses the challenges faced in 3D point cloud segmentation, such as the high dimensionality of point cloud data, noise, and varying point densities. METHODS: The paper compares several commonly used datasets in the field, including the ModelNet, ScanNet, S3DIS, and Semantic 3D datasets, ApploloCar3D, and provides an analysis of the strengths and weaknesses of each dataset. Also provides an overview of the papers that uses Traditional clustering techniques, deep learning-based methods, and hybrid approaches in point cloud semantic segmentation. The report also discusses the benefits and drawbacks of each approach. CONCLUSION: This study sheds light on the state of the art in semantic segmentation of 3D point clouds.