A Unified Generative Framework for Realistic LiDAR Simulation in Autonomous Driving Systems
- 19 December 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 26 (3) , 5013-5025
Abstract
Simulation models for perception sensors are integral components of automotive simulators used for the virtual validation of Autonomous Driving Systems (ADS). They also function as powerful tools for generating synthetic datasets to train deep learning-based perception models. LiDAR is a widely adopted perception sensor in ADS due to its high precision in 3D environment scanning. However, developing realistic LiDAR simulation models is a significant technical challenge. Unrealistic simulations can result in a large gap between the synthesised and real-world point clouds, limiting their effectiveness in perception and planning modules. Recently, deep generative models have emerged as promising solutions to synthesise realistic sensory data. However, for LiDAR simulation, deep generative models have been primarily hybridised with conventional algorithms, leaving unified generative approaches largely unexplored in the literature. Addressing this gap, we propose a unified generative framework to enhance LiDAR simulation fidelity. Our proposed framework projects LiDAR point clouds into depth-reflectance images via a lossless transformation, and employs our novel Controllable Lidar point cloud Generative model, CoLiGen, to translate the images. We extensively evaluate our CoLiGen model, comparing it with the state-of-the-art image-to-image translation models using various metrics to assess the realness, faithfulness, and performance of a downstream perception model. Our results show that CoLiGen exhibits superior performance across most metrics. The dataset and source code for this research are available at https://github.com/hamedhaghighi/CoLiGen.git.Keywords
All Related Versions
Funding Information
- European Commission (101069576)
- Innovate UK (10045139)
- Centre for Doctoral Training to Advance the Deployment of Future Mobility Technologies
This publication has 40 references indexed in Scilit:
- RangeLDM: Fast Realistic LiDAR Point Cloud Generation2024
- Exploring the role of simulator fidelity in the safety validation of learning‐enabled autonomous systemsAI Magazine, 2023
- Learning to Generate Realistic LiDAR Point Clouds2022
- Contrastive Learning for Unpaired Image-to-Image Translation2020
- nuScenes: A Multimodal Dataset for Autonomous Driving2020
- Scalability in Perception for Autonomous Driving: Waymo Open Dataset2020
- LiDARsim: Realistic LiDAR Simulation by Leveraging the Real World2020
- Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain MappingConference on Computer Vision and Pattern Recognition (CVPR), 2019
- Image-to-Image Translation with Conditional Adversarial Networks2017
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015