外观
论文arXiv 2608.153172 个月前
LightLoc++：用于高效室外 LiDAR 定位的传感器鲁棒表征学习
原文链接：LightLoc++: Sensor-Robust Representation Learning for Efficient Outdoor LiDAR Localization（arXiv 2608.15317 · 发布日期：2026-08-15）
LightLoc++: Sensor-Robust Representation Learning for Efficient Outdoor LiDAR Localization
LightLoc++通过跨传感器一致性预训练与高效新场景学习，在多个室外 LiDAR 定位基准验证传感器鲁棒定位。
核心要点
- 现有解耦 SCR 方法依赖预训练骨干，遇到不同 LiDAR 传感器数据时精度明显下降。
- 方法引入 SULID 多 LiDAR 数据集，通过跨传感器一致性学习预训练传感器鲁棒骨干。
- LightLoc++结合样本分类引导和冗余样本下采样，降低回归歧义与大场景计算冗余。
- 多个室外 LiDAR 定位基准显示其性能达到先进水平，新场景训练成本最低；代码和数据集将开放。
验证范围与局限：验证范围为多个室外 LiDAR 定位基准，传感器鲁棒学习基于 SULID 的32、64、128线旋转 LiDAR。
英文摘要 (Abstract)
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.
作者：Wen Li, Shangshu Yu, Dunqiang Liu, Siyu Chen, Qiming Xia, Sheng Ao, Siqi Shen, Cheng Wang, Cheng Wang
来源
本页事实对应的公开页面，以原文为准。