融合几何与神经网络，实现跨设备高精度定位
Hybrid Cross-Device Localization via Neural Metric Learning and Feature Fusion
- 用共享编码器+双分支结构，结合几何与神经方法
- 在两个基准上召回率与精度显著提升，最终得分92.62
- 适合需要跨设备精确定位的机器人与导航应用
我们为CroCoDL 2025挑战赛提出一种混合跨设备定位流程。该方法采用共享检索编码器，并包含两个互补分支：一个基于特征融合与PnP的经典几何分支，以及一个以几何输入为条件的神经前馈分支（MapAnything）用于度量定位。通过神经引导的候选帧裁剪策略，根据平移一致性过滤不可靠地图帧；在Spot场景中，深度条件化定位进一步提升了度量尺度与平移精度。这些组件协同作用，在HYDRO和SUCCU基准上均实现显著的召回率与准确率提升。在挑战赛中，该方法最终获得92.62分（[email protected], 5°）。
原文摘要 · Abstract (English)
We present a hybrid cross-device localization pipeline developed for the CroCoDL 2025 Challenge. Our approach integrates a shared retrieval encoder and two complementary localization branches: a classical geometric branch using feature fusion and PnP, and a neural feed-forward branch (MapAnything) for metric localization conditioned on geometric inputs. A neural-guided candidate pruning strategy further filters unreliable map frames based on translation consistency, while depth-conditioned localization refines metric scale and translation precision on Spot scenes. These components jointly lead to significant improvements in recall and accuracy across both HYDRO and SUCCU benchmarks. Our method achieved a final score of 92.62 ([email protected], 5°) during the challenge.
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。