Guardado en:
Detalles Bibliográficos
Autores principales: Zhu, Minghang, Wang, Zhijing, Guo, Yuxin, Li, Wen, Ao, Sheng, Wang, Cheng
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2602.03198
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915770402865152
author Zhu, Minghang
Wang, Zhijing
Guo, Yuxin
Li, Wen
Ao, Sheng
Wang, Cheng
author_facet Zhu, Minghang
Wang, Zhijing
Guo, Yuxin
Li, Wen
Ao, Sheng
Wang, Cheng
contents LiDAR relocalization aims to estimate the global 6-DoF pose of a sensor in the environment. However, existing regression-based approaches are prone to dynamic or ambiguous scenarios, as they either solely rely on single-frame inference or neglect the spatio-temporal consistency across scans. In this paper, we propose TempLoc, a new LiDAR relocalization framework that enhances the robustness of localization by effectively modeling sequential consistency. Specifically, a Global Coordinate Estimation module is first introduced to predict point-wise global coordinates and associated uncertainties for each LiDAR scan. A Prior Coordinate Generation module is then presented to estimate inter-frame point correspondences by the attention mechanism. Lastly, an Uncertainty-Guided Coordinate Fusion module is deployed to integrate both predictions of point correspondence in an end-to-end fashion, yielding a more temporally consistent and accurate global 6-DoF pose. Experimental results on the NCLT and Oxford Robot-Car benchmarks show that our TempLoc outperforms stateof-the-art methods by a large margin, demonstrating the effectiveness of temporal-aware correspondence modeling in LiDAR relocalization. Our code will be released soon.
format Preprint
id arxiv_https___arxiv_org_abs_2602_03198
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle From Single Scan to Sequential Consistency: A New Paradigm for LIDAR Relocalization
Zhu, Minghang
Wang, Zhijing
Guo, Yuxin
Li, Wen
Ao, Sheng
Wang, Cheng
Computer Vision and Pattern Recognition
LiDAR relocalization aims to estimate the global 6-DoF pose of a sensor in the environment. However, existing regression-based approaches are prone to dynamic or ambiguous scenarios, as they either solely rely on single-frame inference or neglect the spatio-temporal consistency across scans. In this paper, we propose TempLoc, a new LiDAR relocalization framework that enhances the robustness of localization by effectively modeling sequential consistency. Specifically, a Global Coordinate Estimation module is first introduced to predict point-wise global coordinates and associated uncertainties for each LiDAR scan. A Prior Coordinate Generation module is then presented to estimate inter-frame point correspondences by the attention mechanism. Lastly, an Uncertainty-Guided Coordinate Fusion module is deployed to integrate both predictions of point correspondence in an end-to-end fashion, yielding a more temporally consistent and accurate global 6-DoF pose. Experimental results on the NCLT and Oxford Robot-Car benchmarks show that our TempLoc outperforms stateof-the-art methods by a large margin, demonstrating the effectiveness of temporal-aware correspondence modeling in LiDAR relocalization. Our code will be released soon.
title From Single Scan to Sequential Consistency: A New Paradigm for LIDAR Relocalization
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2602.03198