$L^3$:Scene-agnostic Visual Localization in the Wild
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910046109040640 |
|---|---|
| author | Zhang, Yu Zhu, Muhua Xue, Yifei Ji, Tie Lao, Yizhen |
| author_facet | Zhang, Yu Zhu, Muhua Xue, Yifei Ji, Tie Lao, Yizhen |
| contents | Standard visual localization methods typically require offline pre-processing of scenes to obtain 3D structural information for better performance. This inevitably introduces additional computational and time costs, as well as the overhead of storing scene representations. Can we visually localize in a wild scene without any off-line preprocessing step? In this paper, we leverage the online inference capabilities of feed-forward 3D reconstruction networks to propose a novel map-free visual localization framework $L^3$. Specifically, by performing direct online 3D reconstruction on RGB images, followed by two-stage metric scale recovery and pose refinement based on 2D-3D correspondences, $L^3$ achieves high accuracy without the need to pre-build or store any offline scene representations. Extensive experiments demonstrate $L^3$ not only that the performance is comparable to state-of-the-art solutions on various benchmarks, but also that it exhibits significantly superior robustness in sparse scenes (fewer reference images per scene). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_07937 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | $L^3$:Scene-agnostic Visual Localization in the Wild Zhang, Yu Zhu, Muhua Xue, Yifei Ji, Tie Lao, Yizhen Computer Vision and Pattern Recognition Standard visual localization methods typically require offline pre-processing of scenes to obtain 3D structural information for better performance. This inevitably introduces additional computational and time costs, as well as the overhead of storing scene representations. Can we visually localize in a wild scene without any off-line preprocessing step? In this paper, we leverage the online inference capabilities of feed-forward 3D reconstruction networks to propose a novel map-free visual localization framework $L^3$. Specifically, by performing direct online 3D reconstruction on RGB images, followed by two-stage metric scale recovery and pose refinement based on 2D-3D correspondences, $L^3$ achieves high accuracy without the need to pre-build or store any offline scene representations. Extensive experiments demonstrate $L^3$ not only that the performance is comparable to state-of-the-art solutions on various benchmarks, but also that it exhibits significantly superior robustness in sparse scenes (fewer reference images per scene). |
| title | $L^3$:Scene-agnostic Visual Localization in the Wild |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.07937 |