Labeling LiDAR point clouds for training autonomous driving is extremely
expensive and difficult. LiDAR simulation aims at generating realistic LiDAR
data with labels for training and verifying self-driving algorithms more
efficiently. Recently, Neural Radiance Fields (NeRF) have been proposed for
novel view synthesis using implicit reconstruction of 3D scenes. Inspired by
this, we present NeRF-LIDAR, a novel LiDAR simulation method that leverages
real-world information to generate realistic LIDAR point clouds. Different from
existing LiDAR simulators, we use real images and point cloud data collected by
self-driving cars to learn the 3D scene representation, point cloud generation
and label rendering. We verify the effectiveness of our NeRF-LiDAR by training
different 3D segmentation models on the generated LiDAR point clouds. It
reveals that the trained models are able to achieve similar accuracy when
compared with the same model trained on the real LiDAR data. Besides, the
generated data is capable of boosting the accuracy through pre-training which
helps reduce the requirements of the real labeled data.

利用实际数据和图像，我们提出了一种新的 LiDAR 模拟方法 NeRF-LiDAR 用于生成真实的 LiDAR 点云，以便更有效地训练和验证自动驾驶算法，并可以通过预训练来提高准确性。