Scene-aware Human Pose Generation using Transformer.
Jieteng YaoJunjie ChenLi NiuBin ShengPublished in: CoRR (2023)
Keyphrases
- human pose
- static images
- pose estimation
- depth images
- human body
- action recognition
- monocular images
- body parts
- video sequences
- human detection
- human motion
- single image
- human actions
- latent variables
- three dimensional
- machine learning
- input image
- video frames
- depth map
- low resolution
- dynamic scenes
- random fields
- facial expressions
- d objects
- depth estimation
- object recognition
- high quality