Encoder-decoder with Multi-level Attention for 3D Human Shape and Pose Estimation.
Ziniu WanZhengjia LiMaoqing TianJianbo LiuShuai YiHongsheng LiPublished in: CoRR (2021)
Keyphrases
- pose estimation
- pose recovery
- articulated pose
- video codec
- computer vision
- human body
- d objects
- rotation and translation
- degrees of freedom
- decoding process
- position and orientation
- feature points
- human pose estimation
- human upper body
- distributed video coding
- pose parameters
- head pose estimation
- body parts
- shape model
- monocular images
- motion estimation
- human pose
- depth images
- shape descriptors
- rate distortion
- bit rate
- pose estimates
- video coding
- upper body
- implicit polynomial
- object recognition
- human activities
- action recognition
- object pose
- camera pose estimation
- articulated model
- tracking and pose estimation
- vision system