发表机构
Xiamen University; University of Bristol; Northeastern University（厦门大学; 布里斯托大学; 东北大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
LightLoc++通过引入SULID数据集与跨传感器一致性学习预训练传感器鲁棒骨干，结合样本分类引导与冗余样本下采样，实现高效室外激光雷达定位，性能最优且新场景训练成本最低。
AI 中文摘要
场景坐标回归（SCR）在室外激光雷达定位中表现出色，但通常需要针对特定场景进行训练，耗时可达数天，限制了实际部署。近期研究通过将SCR解耦为与场景无关的骨干网络和与场景相关的预测头来提升训练效率，其中骨干网络在源数据集上预训练后，针对新场景时保持冻结状态，仅优化轻量级预测头。然而，我们发现这种范式严重依赖预训练的骨干网络：当激光雷达配置与骨干网络预训练时使用的配置相似时，现有解耦方法可与针对每个新场景完全优化的传统SCR方法性能相当，但在使用不同激光雷达传感器采集的数据集上，其精度会明显下降。这表明高效的激光雷达定位需要能在不同激光雷达配置下捕获稳定场景几何结构的表示。基于此，我们提出LightLoc++，这是一个面向室外激光雷达定位的传感器鲁棒且高效的框架。为支持传感器鲁棒性表示学习，我们引入SULID，这是一个同步的城市多激光雷达数据集，包含具有代表性的32线、64线和128线旋转激光雷达，具备广泛的跨传感器重叠区域和多样的城市场景。利用SULID，我们通过跨传感器一致性学习预训练出传感器鲁棒的骨干网络。LightLoc++还通过引入样本分类引导和冗余样本下采样，保留了新场景的高效学习能力，这两种技术可减少大规模室外场景中的回归歧义与计算冗余。在多个室外激光雷达定位基准上的大量实验表明，LightLoc++在对比方法中实现了最先进的定位性能，同时新场景训练成本最低。代码和数据集将在该httpsURL处提供。
英文摘要
Scene coordinate regression (SCR) achieves strong performance in outdoor LiDAR localization, but it usually requires scene-specific training that can take days, limiting practical deployment. Recent works improve training efficiency by decoupling SCR into a scene-agnostic backbone and scene-specific prediction heads, where the backbone is pretrained on source datasets and frozen for new scenes, and only lightweight heads are optimized. However, we find that this paradigm heavily depends on the pretrained backbone. Existing decoupled methods can match conventional SCR methods fully optimized for each new scene when LiDAR configurations are similar to those used during backbone pretraining, but their accuracy drops noticeably on datasets collected with different LiDAR sensors. This suggests that efficient LiDAR localization requires representations that capture stable scene geometry across LiDAR configurations. Motivated by this observation, we propose LightLoc++, a sensor-robust and efficient outdoor LiDAR localization framework. To support sensor-robust representation learning, we introduce SULID, a synchronized urban multi-LiDAR dataset with representative 32-, 64-, and 128-beam rotating LiDARs, extensive cross-sensor overlap, and diverse urban scenes. Using SULID, we pretrain a sensor-robust backbone through cross-sensor consistency learning. LightLoc++ further preserves efficient new-scene learning by incorporating sample classification guidance and redundant sample downsampling, which reduce regression ambiguity and computational redundancy in large-scale outdoor scenes. Extensive experiments on multiple outdoor LiDAR localization benchmarks demonstrate that LightLoc++ achieves state-of-the-art localization performance with the lowest new-scene training cost among compared methods. Code and dataset will be made available at https://github.com/liw95/LightLoc-PlusPlus.
Commentsv2: corrected author list (Shaoyang Chen was inadvertently omitted in v1)
