A strengthened soft-point registration network for LiDAR point cloud registration
PLOS One · 18.08.2026 · 21 (8) · e0355292
DOI: 10.1371/journal.pone.0355292 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 18.08.2026. Verfasst von Yijie Chen und 6 weiteren Autor:innen. Beteiligte Einrichtung: Naval University of Engineering, Wuhan, China. Hauptthemen laut MEDLINE: Robotics. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Scientific and Technological Research Project of Jiangxi Provincial Department of Education.
Abstract (Originalsprache)
In complex environments, fast and accurate registration of LiDAR point clouds is crucial for ensuring the safety of robot environmental perception and other LiDAR-based applications. Existing point cloud registration methods typically rely on feature matching to find correspondences between points and use RANSAC to estimate transformation parameters after filtering out incorrect correspondence\s. However, this approach introduces two problems: first, in partial registration scenarios, where point cloud shapes are incomplete, feature matching becomes unreliable. Second, the significant number of iterations required by RANSAC increases the time needed for registration. To address these issues, this paper introduces a strengthened soft-point registration network (SPRN) based on cross-attention—an end-to-end registration network that is feature-matching-free and RANSAC-free. First, the model independently generates k soft points for the source and target point clouds, producing k point-to-point correspondences. The rigid transformation parameters are then directly estimated from these k correspondences. Each soft point is obtained by a weighted aggregation of all superpoints in the source or target cloud, where the weights are automatically assigned by the attention mechanism. Although the local geometric structures at the corresponding locations may differ due to incompleteness, the attention mechanism focuses on the shared parts and filters out the inconsistent ones, making these soft-point correspondences more reliable than those obtained via feature matching. Moreover, our method avoids the feature-matching and RANSAC steps, resulting in a much faster runtime. Experiments conducted on the real-world datasets 3DMatch, 3DLoMatch, KITTI, and WHU-TLS demonstrate that this method achieves faster point cloud registration while maintaining registration accuracy.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Naval University of Engineering, Wuhan, China.
- School of Mathematics and Computer Sciences, Nanchang University, Nanchang, China.
- School of Computer and Information Engineering, Nanchang Institute of Technology, Nanchang, China.
ORCID-Profile: Yijie Chen, Zeyun Wan
Förderung
- National Natural Science Foundation of China
- Scientific and Technological Research Project of Jiangxi Provincial Department of Education
Zitieren
APA
Chen, Y., Tian, B., Wan, Z., Fan, S., Chen, M., Wu, Y., & Li, C. (2026). A strengthened soft-point registration network for LiDAR point cloud registration. PLOS One, 21(8), e0355292. https://doi.org/10.1371/journal.pone.0355292
Vancouver
Chen Y, Tian B, Wan Z, Fan S, Chen M, Wu Y, et al. A strengthened soft-point registration network for LiDAR point cloud registration. PLOS One. 2026;21(8):e0355292. doi:10.1371/journal.pone.0355292
BibTeX
@article{Chen2026,
author = {Chen, Yijie and Tian, Bin and Wan, Zeyun and Fan, Shichao and Chen, Mingxing and Wu, Yi and Li, Chunquan},
title = {A strengthened soft-point registration network for LiDAR point cloud registration},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {8},
pages = {e0355292},
doi = {10.1371/journal.pone.0355292}
}
EUVIMED