通过建模多帧一致性，提升激光雷达定位在动态环境中的鲁棒性。
From Single Scan to Sequential Consistency: A New Paradigm for LIDAR Relocalization
- 引入全局坐标预测与注意力匹配，实现跨帧点对应关系建模。
- 在NCLT和Oxford Robot-Car数据集上显著优于现有方法。
- 适合需要高精度时序一致性的自动驾驶定位任务。
LiDAR重定位旨在估计传感器在环境中的全局6-DoF位姿。然而，现有基于回归的方法在动态或模糊场景中表现不佳，因其仅依赖单帧推理或忽略扫描间的时空一致性。本文提出TempLoc框架，通过有效建模序列一致性增强定位鲁棒性。首先引入全局坐标估计模块，为每帧LiDAR扫描预测点级全局坐标及不确定性；随后设计先验坐标生成模块，利用注意力机制估计帧间点对应关系；最后采用不确定性引导的坐标融合模块，端到端整合对应关系，得到更时序一致且精确的全局6-DoF位姿。在NCLT和Oxford Robot-Car基准上的实验表明，TempLoc显著超越当前最优方法，验证了时序感知对应建模的有效性。代码将很快开源。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。