Robust Scene Coordinate Regression via Geometrically-Consistent Global Descriptors
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909984148684800 |
|---|---|
| author | Nguyen, Son Tung Fontan, Alejandro Milford, Michael Fischer, Tobias |
| author_facet | Nguyen, Son Tung Fontan, Alejandro Milford, Michael Fischer, Tobias |
| contents | Recent learning-based visual localization methods use global descriptors to disambiguate visually similar places, but existing approaches often derive these descriptors from geometric cues alone (e.g., covisibility graphs), limiting their discriminative power and reducing robustness in the presence of noisy geometric constraints. We propose an aggregator module that learns global descriptors consistent with both geometrical structure and visual similarity, ensuring that images are close in descriptor space only when they are visually similar and spatially connected. This corrects erroneous associations caused by unreliable overlap scores. Using a batch-mining strategy based solely on the overlap scores and a modified contrastive loss, our method trains without manual place labels and generalizes across diverse environments. Experiments on challenging benchmarks show substantial localization gains in large-scale environments while preserving computational and memory efficiency. Code is available at https://github.com/sontung/robust_scr. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_17226 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Robust Scene Coordinate Regression via Geometrically-Consistent Global Descriptors Nguyen, Son Tung Fontan, Alejandro Milford, Michael Fischer, Tobias Computer Vision and Pattern Recognition Recent learning-based visual localization methods use global descriptors to disambiguate visually similar places, but existing approaches often derive these descriptors from geometric cues alone (e.g., covisibility graphs), limiting their discriminative power and reducing robustness in the presence of noisy geometric constraints. We propose an aggregator module that learns global descriptors consistent with both geometrical structure and visual similarity, ensuring that images are close in descriptor space only when they are visually similar and spatially connected. This corrects erroneous associations caused by unreliable overlap scores. Using a batch-mining strategy based solely on the overlap scores and a modified contrastive loss, our method trains without manual place labels and generalizes across diverse environments. Experiments on challenging benchmarks show substantial localization gains in large-scale environments while preserving computational and memory efficiency. Code is available at https://github.com/sontung/robust_scr. |
| title | Robust Scene Coordinate Regression via Geometrically-Consistent Global Descriptors |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.17226 |