Towards Real-Time and Adaptable LiDAR Scene Completion

Summary

We present RapidLiDAR, a LiDAR scene completion method that treats initialization as a learned, data-driven component. An adaptive initialization module predicts spatially varying displacement for each partial input point, avoiding manual noise tuning. A multi-scale reconstruction module refines point positions using voxel and BEV feature maps. On SemanticKITTI and KITTI-360, our method achieves state-of-the-art completion performance while completing a full scene in 0.1 seconds—2.3 times faster than the fastest prior method—matching the 10 Hz acquisition rate of typical automotive LiDAR sensors.