Physics-Constrained Variational Autoencoders for Density Compensation in High-Rise LiDAR Point Clouds
Automation · 15.05.2026 · 7 (3) · 76
DOI: 10.3390/automation7030076 ↗Kurz gefasst
Fachartikel in der Zeitschrift Automation, online erschienen am 15.05.2026. Verfasst von Kohei Arai. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
High-rise LiDAR scanning produces vertically sparse point clouds where upper-layer defects are hardest to detect due to inverse-square ranging law (1/r2) density gradients, noise contamination, and complex geometries. This paper presents PC-TowerNet, a physics-aware AI pipeline that achieves state-of-the-art reconstruction through sequential modules: (1) 50D geometric feature classification outperforming CloudCompare SOR (100% accuracy vs. 91.3% retention); (2) Physics-Constrained VAE (PC-VAE) recovering 28.7 ± 2.1% upper density vs. 8.3 ± 1.7% standard VAE; (3) multi-modal PointNet++/GNN/Transformer fusion; and (4) Bayesian uncertainty maps (ECE = 0.042 ± 0.008). Synthetic tower evaluation (10 × 5 seeds) demonstrates 48.9% surface smoothness improvement and 38.2% volume error reduction over tuned RANSAC baselines, with clear paths to real-data validation.
Zitieren
APA
Arai, K. (2026). Physics-Constrained Variational Autoencoders for Density Compensation in High-Rise LiDAR Point Clouds. Automation, 7(3), 76. https://doi.org/10.3390/automation7030076
Vancouver
Arai K. Physics-Constrained Variational Autoencoders for Density Compensation in High-Rise LiDAR Point Clouds. Automation. 2026;7(3):76. doi:10.3390/automation7030076
BibTeX
@article{Arai2026,
author = {Arai, Kohei},
title = {Physics-Constrained Variational Autoencoders for Density Compensation in High-Rise LiDAR Point Clouds},
journal = {Automation},
year = {2026},
volume = {7},
number = {3},
pages = {76},
doi = {10.3390/automation7030076}
}
EUVIMED