| title | Towards Real-Time and Adaptable LiDAR Scene Completion |
|---|---|
| authors | Azhar Hussian, Martin Vossiek, Vasileios Belagiannis |
| date | 2026-08-17 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2608.16490 |
| affiliation | FAU Erlangen-Nürnberg |
| upvotes | 2 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | LiDAR scene completion is a key component of 3D perception in autonomous driving, where the scene must be completed in real time to be usable in downstream tasks. Existing approaches typically follow an initialize-and-refine paradigm, in which a coarse initialization of the scene is first constructed, then refined into complete 3D geometry. Generative models are slower because they iteratively refine random Gaussian noise into the scene, while non-generative methods perturb the partial scene with a fixed noise scale, which limits coverage of large gaps and occluded regions and requires manual recalibration for each new sensor configuration. We present RapidLiDAR, a LiDAR scene completion method that treats the initialization itself as a learned, data-driven component. We propose an adaptive initialization module that predicts a spatially varying displacement for each partial input point, expanding the partial observations into a coarse scene initialization adapted to the local geometry, without requiring manual noise tuning. To refine this coarse initialization into a complete and coherent scene, we additionally propose a multi-scale reconstruction module that further refines point positions by querying multi-scale 3D voxel and 2D BEV feature maps constructed from the input scan. By replacing point-neighborhood operators such as farthest point sampling and k-nearest neighbor search with voxel- and BEV-based feature extraction, our architecture is faster and can handle different input resolutions by design. Experiments on SemanticKITTI and KITTI-360 show that our method achieves completion performance on par with the state of the art while completing a full scene in 0.1 seconds, which is 2.3 times faster than the fastest prior method. This matches the 10 Hz acquisition rate of typical automotive LiDAR sensors, taking a step toward real-time LiDAR scene completion. |
cite
@misc{hussian2026towards,
title={Towards Real-Time and Adaptable LiDAR Scene Completion},
author={Azhar Hussian and Martin Vossiek and Vasileios Belagiannis},
year={2026},
eprint={2608.16490},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2608.16490}
}