Learning Scene Geometry for Visual Localization in Challenging Conditions
Résumé
We propose a new approach for outdoor large scale image based localization that can deal with challenging scenarios like cross-season, cross-weather, day/night and long-term localization. The key component of our method is a new learned global image descriptor, that can effectively benefit from scene geometry information during training. At test time, our system is capable of inferring the depth map related to the query image and use it to increase localization accuracy. We are able to increase recall@1 performances by 2.15% on cross-weather and long-term localization scenario and by 4.24% points on a challenging winter/summer localization sequence versus state-of-the-art methods. Our method can also use weakly annotated data to localize night images across a reference dataset of daytime images.
Mots clés
- query image
- summer localization sequence
- winter localization sequence
- night images
- long-term localization scenario
- object detection
- learning (artificial intelligence)
- image retrieval
- Robots
- Image reconstruction
- Geometry
- feature extraction
- Visualization
- Training
- Decoding
- cross-weather
- robot vision
- daytime images
- learning scene geometry
- visual localization
- outdoor large scale image
- cross-season
- learned global image descriptor
- scene geometry information
- depth map
- image colour analysis
- localization accuracy
| Origine | Fichiers produits par l'(les) auteur(s) |
|---|---|
| Licence |