PoseAgent: Budget-Constrained 6D Object Pose Estimation via Reinforcement Learning.
Alexander KrullEric BrachmannSebastian NowozinFrank MichelJamie ShottonCarsten RotherPublished in: CVPR (2017)
Keyphrases
- pose estimation
- d objects
- viewpoint
- human body
- object recognition
- multi view
- range data
- multiple views
- body parts
- three dimensional
- position and orientation
- shape descriptors
- focal length
- degrees of freedom
- depth images
- human pose
- object classes
- pose parameters
- geometric invariants
- invariant recognition
- single view
- machine learning
- control points
- surface patches