Point cloud feature edge point curve fitting
Optics Letters · 01.08.2026 · 51 (15) · 4252
DOI: 10.1364/ol.609161 ↗Kurz gefasst
Fachartikel in der Zeitschrift Optics Letters, online erschienen am 23.07.2026. Verfasst von Kai Wan und 3 weiteren Autor:innen. Die Arbeit nennt 10 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Structured light edge point clouds suffer from scattering noise and non-uniform sampling, rendering traditional discrete fitting inadequate. We propose a one-stage parametric reconstruction framework that bypasses intermediate discrete representations. By integrating mask-driven dynamic control point regression with a differentiable geometric constraint solver, our model directly predicts topologically correct primitives (Bézier curves, lines, arcs) from scattered points. Demonstrating high robustness against scanning noise, it achieves a Chamfer Distance of 0.0038, and a Hausdorff Distance of 0.0764 on the ABC dataset. Preliminary self-consistency tests on real-world sensors demonstrate the method's robustness, offering a potential 3D edge parameterization solution for reverse engineering.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Wan, K., Xia, J., Zhang, B., & Liu, W. (2026). Point cloud feature edge point curve fitting. Optics Letters, 51(15), 4252. https://doi.org/10.1364/ol.609161
Vancouver
Wan K, Xia J, Zhang B, Liu W. Point cloud feature edge point curve fitting. Optics Letters. 2026;51(15):4252. doi:10.1364/ol.609161
BibTeX
@article{Wan2026,
author = {Wan, Kai and Xia, Junjie and Zhang, Baoshen and Liu, Wei},
title = {Point cloud feature edge point curve fitting},
journal = {Optics Letters},
year = {2026},
volume = {51},
number = {15},
pages = {4252},
doi = {10.1364/ol.609161}
}
EUVIMED