Toward Physics-Aware Deep Learning Architectures for LiDAR Intensity Simulation

TL;DR

This paper enhances LiDAR intensity simulation for autonomous vehicles by integrating physics-based factors like incidence angle into deep learning models, demonstrating improved accuracy with GAN and CNN architectures on real datasets.

Contribution

It introduces the incorporation of incidence angle as an input in deep learning models for LiDAR intensity simulation, comparing CNN and GAN architectures.

Findings

Pix2Pix GAN outperforms U-NET CNN in intensity prediction.

Adding incidence angle improves model performance.

Physics-aware inputs enhance deep learning-based LiDAR simulation.

Abstract

Autonomous vehicles (AVs) heavily rely on LiDAR perception for environment understanding and navigation. LiDAR intensity provides valuable information about the reflected laser signals and plays a crucial role in enhancing the perception capabilities of AVs. However, accurately simulating LiDAR intensity remains a challenge due to the unavailability of material properties of the objects in the environment, and complex interactions between the laser beam and the environment. The proposed method aims to improve the accuracy of intensity simulation by incorporating physics-based modalities within the deep learning framework. One of the key entities that captures the interaction between the laser beam and the objects is the angle of incidence. In this work we demonstrate that the addition of the LiDAR incidence angle as a separate input to the deep neural networks significantly enhances the results. We present a comparative study between two prominent deep learning architectures: U-NET a Convolutional Neural Network (CNN), and Pix2Pix a Generative Adversarial Network (GAN). We implemented these two architectures for the intensity prediction task and used SemanticKITTI and VoxelScape datasets for experiments. The comparative analysis reveals that both architectures benefit from the incidence angle as an additional input. Moreover, the Pix2Pix architecture outperforms U-NET, especially when the incidence angle is incorporated.