Temporal-Aware Fusion for Robust Outdoor LiDAR Localization

2026-09-28

AI Summary

This study addresses the limited robustness of existing LiDAR relocalization methods in dynamic or ambiguous scenes, where temporal and spatial consistency is often neglected. To this end, we propose TempLoc, a novel framework that introduces global coordinate estimation, prior coordinate generation, and an uncertainty-guided fusion module. Specifically, TempLoc leverages attention mechanisms to model inter-frame point correspondences and employs uncertainty quantification to achieve end-to-end fusion of multi-source predictions, thereby effectively enhancing sequence consistency. Experimental results on the NCLT and Oxford RobotCar benchmarks demonstrate that TempLoc significantly outperforms current state-of-the-art methods. These findings validate the effectiveness of temporally aware modeling in improving the accuracy of 6-DoF pose estimation for LiDAR-based relocalization.

Abstract

LiDAR relocalization aims to estimate the global 6-DoF pose of a sensor in the environment. However, existing regression-based approaches often encounter limitations in dynamic or ambiguous scenarios, as they typically prioritize single-frame inference, leaving the potential of spatio-temporal consistency across scans not fully explored. In this paper, we propose a Temporal-aware Localization framework (TempLoc) designed to enhance the robustness of outdoor 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 RobotCar benchmarks show that our TempLoc outperforms state-of-the-art methods by a large margin, demonstrating the effectiveness of temporal-aware correspondence modeling in LiDAR relocalization.

Problem

• LiDAR relocalization
• 6-DoF pose estimation
• spatio-temporal consistency
• outdoor localization
• dynamic scenarios

Innovation

• Temporal-Aware Fusion
• LiDAR Relocalization
• Uncertainty-Guided Coordinate Fusion
• Attention Mechanism
• 6-DoF Pose Estimation