A Brief Survey on 3D Semantic Segmentation of Lidar Point Cloud with Deep Learning

Abstract

3D semantic segmentation is a fundamental task for many applications like Autonomous Driving. Recent work shows the capability of Deep Neural Networks in labelling 3D point clouds of major sensors like: LiDAR and Radar. The main challenge that faces this task is the nature of 3D point clouds being unordered and spatially-uncorrelated, making it different in terms of processing algorithms than the images. In addition to that, a point cloud usually needs higher processing power than the images if it's processed in its raw nature. In this paper, we will review different deep learning methods for 3D semantic segmentation, examples of the widely used datasets in addition to the evaluation metrics.