Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraints.
Reza MahjourianMartin WickeAnelia AngelovaPublished in: CoRR (2018)
Keyphrases
- ego motion
- geometric constraints
- camera motion
- epipolar geometry
- moving camera
- video sequences
- field of view
- dynamic scenes
- optical flow
- image sequences
- d scene
- stereo camera
- depth information
- camera calibration
- image motion
- scene structure
- video data
- robust estimation
- space time
- motion parameters
- flow field
- multi camera
- optic flow
- multiple images
- motion field
- multi view
- stereo pair
- multiple cameras
- velocity field
- motion estimation
- bundle adjustment
- video camera
- computer vision
- viewpoint
- depth images
- stereo images
- video surveillance
- moving objects
- depth map
- multiple views