LiDAR Sensor modeling and Data augmentation with GANs for Autonomous driving

TL;DR

This paper proposes a novel method using CycleGANs to generate realistic LiDAR data from simulated and lower-resolution sources, enhancing data augmentation for autonomous driving without requiring paired datasets.

Contribution

It introduces a CycleGAN-based approach for unpaired LiDAR sensor modeling and data augmentation, addressing the challenge of lacking paired datasets in autonomous driving.

Findings

High-quality realistic LiDAR generation from simulated data.

Effective super-resolution of LiDAR data.

Potential to improve autonomous driving data augmentation.

Abstract

In the autonomous driving domain, data collection and annotation from real vehicles are expensive and sometimes unsafe. Simulators are often used for data augmentation, which requires realistic sensor models that are hard to formulate and model in closed forms. Instead, sensors models can be learned from real data. The main challenge is the absence of paired data set, which makes traditional supervised learning techniques not suitable. In this work, we formulate the problem as image translation from unpaired data and employ CycleGANs to solve the sensor modeling problem for LiDAR, to produce realistic LiDAR from simulated LiDAR (sim2real). Further, we generate high-resolution, realistic LiDAR from lower resolution one (real2real). The LiDAR 3D point cloud is processed in Bird-eye View and Polar 2D representations. The experimental results show a high potential of the proposed approach.