Geometric Loss Functions for Camera Pose Regression with Deep Learning.
Alex KendallRoberto CipollaPublished in: CVPR (2017)
Keyphrases
- loss function
- deep learning
- camera pose
- reproducing kernel hilbert space
- support vector
- geometric constraints
- structure from motion
- unsupervised learning
- feature points
- pairwise
- pose estimation
- point correspondences
- bundle adjustment
- urban environments
- position and orientation
- camera motion
- focal length
- single view
- machine learning
- weakly supervised
- camera calibration
- camera parameters
- mental models
- decision trees
- support vector machine
- model selection
- image processing
- closed form solutions
- high dimensional
- graph cuts