NeRF-LiDAR: Generating Realistic LiDAR Point Clouds with Neural Radiance Fields
This addresses the expensive labeling problem for autonomous driving researchers and engineers, offering an incremental improvement in simulation techniques.
The paper tackles the high cost of labeling LiDAR point clouds for autonomous driving by proposing NeRF-LiDAR, a simulation method that generates realistic LiDAR data using real-world images and point clouds, achieving similar accuracy in 3D segmentation models as real data and reducing the need for labeled data through pre-training.
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.