ViTPose++: Vision Transformer for Generic Body Pose Estimation.
Yufei XuJing ZhangQiming ZhangDacheng TaoPublished in: IEEE Trans. Pattern Anal. Mach. Intell. (2024)
Keyphrases
- pose estimation
- human body
- computer vision
- body parts
- d objects
- articulated model
- degrees of freedom
- monocular images
- human pose estimation
- feature points
- upper body
- markerless
- vision system
- invariant recognition
- head pose estimation
- human pose
- motion capture
- articulated pose
- problems in computer vision
- pose parameters
- human motion
- hand pose
- position and orientation
- object recognition and pose estimation
- machine learning
- body pose
- tracking and pose estimation
- image sequences
- object pose
- object recognition
- pose estimates
- human upper body
- rotation and translation
- generic model
- free form
- depth images