Homography-Based Loss Function for Camera Pose Regression.
Clémentin BoittiauxRicard MarxerClaire DuneAurélien ArnaubecVincent HugelPublished in: CoRR (2022)
Keyphrases
- loss function
- camera pose
- feature points
- camera motion
- intrinsic parameters
- reproducing kernel hilbert space
- gradient boosting
- support vector
- point correspondences
- pose estimation
- epipolar geometry
- point features
- fundamental matrix
- structure from motion
- camera pose estimation
- bundle adjustment
- pairwise
- focal length
- camera calibration
- camera parameters
- position and orientation
- single view
- ground plane
- image sequences
- video sequences
- urban environments
- line segments
- line features
- scene structure
- optical flow
- linear regression
- moving objects
- geometric constraints
- model selection
- decision trees
- multi view
- trifocal tensor
- kernel function