LU-Net: An Efficient Network for 3D LiDAR Point Cloud Semantic Segmentation Based on End-to-End-Learned 3D Features and U-Net

TL;DR

LU-Net introduces an efficient end-to-end deep learning approach for 3D LiDAR point cloud semantic segmentation by combining learned 3D features with a 2D U-Net, achieving high accuracy and real-time performance.

Contribution

The paper presents a novel method that projects 3D point cloud features into 2D images for segmentation, outperforming existing methods in accuracy and efficiency.

Findings

Outperforms state-of-the-art on KITTI dataset

Operates at 24fps on a single GPU

Effective real-time semantic segmentation for LiDAR data

Abstract

We propose LU-Net -- for LiDAR U-Net, a new method for the semantic segmentation of a 3D LiDAR point cloud. Instead of applying some global 3D segmentation method such as PointNet, we propose an end-to-end architecture for LiDAR point cloud semantic segmentation that efficiently solves the problem as an image processing problem. We first extract high-level 3D features for each point given its 3D neighbors. Then, these features are projected into a 2D multichannel range-image by considering the topology of the sensor. Thanks to these learned features and this projection, we can finally perform the segmentation using a simple U-Net segmentation network, which performs very well while being very efficient. In this way, we can exploit both the 3D nature of the data and the specificity of the LiDAR sensor. This approach outperforms the state-of-the-art by a large margin on the KITTI dataset, as our experiments show. Moreover, this approach operates at 24fps on a single GPU. This is above the acquisition rate of common LiDAR sensors which makes it suitable for real-time applications.