Search papers, labs, and topics across Lattice.
This paper introduces a physics-informed conditional Wasserstein GAN (PICWGAN) to generate realistic LiDAR data under adverse weather by incorporating constraints for signal attenuation and geometry-consistent degradations. The approach minimizes the sim-to-real gap by enforcing physical principles during training, leading to more realistic intensity patterns. Experiments on real-world datasets (CADC, Boreas, VoxelScape) show that models trained on PICWGAN-enhanced data achieve 3D object detection performance comparable to models trained on real-world data, outperforming other simulation methods.
Closing the sim-to-real gap for LiDAR in adverse weather is now possible: physics-informed GANs generate synthetic data that allows models to perform as well as if trained on real-world 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.
