VI-Net: Boosting Category-level 6D Object Pose Estimation via Learning Decoupled Rotations on the Spherical Representations.
Jiehong LinZewei WeiYabin ZhangKui JiaPublished in: CoRR (2023)
Keyphrases
- pose estimation
- d objects
- human body
- learning algorithm
- object recognition
- viewpoint
- computer vision
- three dimensional
- pose parameters
- shape descriptors
- multi view
- invariant recognition
- recognition and pose estimation
- image descriptors
- range data
- multiple views
- feature points
- supervised learning
- multiscale
- multi task
- visual recognition
- object detection
- machine learning