Boosting 3-DoF Ground-to-Satellite Camera Localization Accuracy via Geometry-Guided Cross-View Transformer.
Yujiao ShiFei WuAkhil PerincherryAnkit VoraHongdong LiPublished in: ICCV (2023)
Keyphrases
- cross view
- similarity search
- scene geometry
- graph embedding
- camera calibration
- hand held
- three dimensional
- field of view
- learning algorithm
- multiple cameras
- camera parameters
- person re identification
- camera motion
- structure from motion
- vision system
- camera network
- pose estimation
- surveillance system
- position and orientation
- real scenes
- dimensionality reduction
- video surveillance
- multi view
- camera views
- high dimensional
- data sets