Multi-view object pose estimation from correspondence distributions and epipolar geometry.
Rasmus Laurvig HaugaardThorbjørn Mosekjær IversenPublished in: ICRA (2023)
Keyphrases
- pose estimation
- multi view
- d objects
- epipolar geometry
- point correspondences
- multiple views
- feature points
- fundamental matrix
- image correspondences
- shape from silhouettes
- single view
- visual hull
- multiple cameras
- epipolar lines
- position and orientation
- viewpoint
- image pairs
- geometric constraints
- human body
- three dimensional
- object recognition
- bundle adjustment
- pose parameters
- photometric stereo
- camera calibration
- feature matching
- body parts
- rigid objects
- range data
- depth map
- stereo pair
- curved surfaces
- camera motion
- dynamic scenes
- camera parameters
- camera positions
- motion parameters
- view synthesis
- depth images
- ground plane
- uncalibrated cameras
- camera views
- surface reconstruction
- semi supervised
- machine learning
- computer vision
- stereo correspondence
- articulated objects
- image sequences
- high resolution