Learning to Generate Realistic LiDAR Point Clouds
This work addresses the need for realistic LiDAR data generation in autonomous driving and robotics, offering a novel method for point cloud densification and conditional sampling without retraining.
The paper tackles the problem of generating realistic LiDAR point clouds by introducing LiDARGen, a generative model that produces diverse and high-quality samples with physical feasibility and controllability, validated on KITTI-360 and NuScenes datasets with results showing more realistic outputs than other models.
We present LiDARGen, a novel, effective, and controllable generative model that produces realistic LiDAR point cloud sensory readings. Our method leverages the powerful score-matching energy-based model and formulates the point cloud generation process as a stochastic denoising process in the equirectangular view. This model allows us to sample diverse and high-quality point cloud samples with guaranteed physical feasibility and controllability. We validate the effectiveness of our method on the challenging KITTI-360 and NuScenes datasets. The quantitative and qualitative results show that our approach produces more realistic samples than other generative models. Furthermore, LiDARGen can sample point clouds conditioned on inputs without retraining. We demonstrate that our proposed generative model could be directly used to densify LiDAR point clouds. Our code is available at: https://www.zyrianov.org/lidargen/