Hybrid Cross-Device Localization via Neural Metric Learning and Feature Fusion
This work addresses localization accuracy for robotics or AR applications, but it appears incremental as it builds on existing methods like PnP and neural networks.
The paper tackled cross-device localization by integrating a shared retrieval encoder with geometric and neural branches, achieving a final score of 92.62 (R@0.5m, 5°) on the CroCoDL 2025 Challenge benchmarks.
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 (R@0.5m, 5°) during the challenge.