Simulating Realistic LiDAR Data Under Adverse Weather for Autonomous Vehicles: A Physics-Informed Learning Approach
This addresses the challenge of robust perception for autonomous vehicles in adverse weather, representing an incremental improvement over existing simulation methods.
The paper tackled the problem of generating realistic LiDAR data for autonomous vehicles under adverse weather by developing a physics-informed learning framework, which reduced the sim-to-real gap and improved 3D object detection performance to levels comparable to models trained on real data.
Accurate LiDAR simulation is crucial for autonomous driving, especially under adverse weather conditions. Existing methods struggle to capture the complex interactions between LiDAR signals and atmospheric phenomena, leading to unrealistic representations. This paper presents a physics-informed learning framework (PICWGAN) for generating realistic LiDAR data under adverse weather conditions. By integrating physicsdriven constraints for modeling signal attenuation and geometryconsistent degradations into a physics-informed learning pipeline, the proposed method reduces the sim-to-real gap. Evaluations on real-world datasets (CADC for snow, Boreas for rain) and the VoxelScape dataset show that our approach closely mimics realworld intensity patterns. Quantitative metrics, including MSE, SSIM, KL divergence, and Wasserstein distance, demonstrate statistically consistent intensity distributions. Additionally, models trained on data enhanced by our framework outperform baselines in downstream 3D object detection, achieving performance comparable to models trained on real-world data. These results highlight the effectiveness of the proposed approach in improving the realism of LiDAR data and enabling robust perception under adverse weather conditions.