Physically Based Neural LiDAR Resimulation
This work addresses the need for more realistic LiDAR simulation in fields like autonomous driving and 3D reconstruction, though it appears incremental as it builds on existing NVS methods by adding sensor-specific modeling.
The paper tackles the problem of insufficiently addressed LiDAR-specific effects in simulation by explicitly modeling sensor characteristics like rolling shutter and laser power variations, achieving more accurate LiDAR simulation compared to state-of-the-art methods with demonstrated quantitative and qualitative improvements.
Methods for Novel View Synthesis (NVS) have recently found traction in the field of LiDAR simulation and large-scale 3D scene reconstruction. While solutions for faster rendering or handling dynamic scenes have been proposed, LiDAR specific effects remain insufficiently addressed. By explicitly modeling sensor characteristics such as rolling shutter, laser power variations, and intensity falloff, our method achieves more accurate LiDAR simulation compared to existing techniques. We demonstrate the effectiveness of our approach through quantitative and qualitative comparisons with state-of-the-art methods, as well as ablation studies that highlight the importance of each sensor model component. Beyond that, we show that our approach exhibits advanced resimulation capabilities, such as generating high resolution LiDAR scans in the camera perspective. Our code and the resulting dataset are available at https://github.com/richardmarcus/PBNLiDAR.