BEV-SLD: Self-Supervised Scene Landmark Detection for Global Localization with LiDAR Bird's-Eye View Images
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_ | 1866910057609822208 |
|---|---|
| author | Skuddis, David Ress, Vincent Zhang, Wei Nyako, Vincent Ofosu Haala, Norbert |
| author_facet | Skuddis, David Ress, Vincent Zhang, Wei Nyako, Vincent Ofosu Haala, Norbert |
| contents | We present BEV-SLD, a LiDAR global localization method building on the Scene Landmark Detection (SLD) concept. Unlike scene-agnostic pipelines, our self-supervised approach leverages bird's-eye-view (BEV) images to discover scene-specific patterns at a prescribed spatial density and treat them as landmarks. A consistency loss aligns learnable global landmark coordinates with per-frame heatmaps, yielding consistent landmark detections across the scene. Across campus, industrial, and forest environments, BEV-SLD delivers robust localization and achieves strong performance compared to state-of-the-art methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_17159 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | BEV-SLD: Self-Supervised Scene Landmark Detection for Global Localization with LiDAR Bird's-Eye View Images Skuddis, David Ress, Vincent Zhang, Wei Nyako, Vincent Ofosu Haala, Norbert Computer Vision and Pattern Recognition Robotics We present BEV-SLD, a LiDAR global localization method building on the Scene Landmark Detection (SLD) concept. Unlike scene-agnostic pipelines, our self-supervised approach leverages bird's-eye-view (BEV) images to discover scene-specific patterns at a prescribed spatial density and treat them as landmarks. A consistency loss aligns learnable global landmark coordinates with per-frame heatmaps, yielding consistent landmark detections across the scene. Across campus, industrial, and forest environments, BEV-SLD delivers robust localization and achieves strong performance compared to state-of-the-art methods. |
| title | BEV-SLD: Self-Supervised Scene Landmark Detection for Global Localization with LiDAR Bird's-Eye View Images |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2603.17159 |