Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2601.22551 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910005537538048 |
|---|---|
| author | Lin, Meixia Liu, Mingkai Peng, Shuxue Fan, Dikai Gu, Shengyu Huang, Xianliang Ye, Haoyang Liu, Xiao |
| author_facet | Lin, Meixia Liu, Mingkai Peng, Shuxue Fan, Dikai Gu, Shengyu Huang, Xianliang Ye, Haoyang Liu, Xiao |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_22551 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Hybrid Cross-Device Localization via Neural Metric Learning and Feature Fusion Lin, Meixia Liu, Mingkai Peng, Shuxue Fan, Dikai Gu, Shengyu Huang, Xianliang Ye, Haoyang Liu, Xiao Computer Vision and Pattern Recognition 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. |
| title | Hybrid Cross-Device Localization via Neural Metric Learning and Feature Fusion |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.22551 |