Decanus to Legatus: Synthetic training for 2D-3D human pose lifting.

Yue Zhu David Picard

Published in: CoRR (2022)

Keyphrases

human pose
pose estimation
human body
action recognition
body parts
monocular images
computer vision
human motion
feature points
wavelet transform
training set
decision trees
higher order
object recognition
random fields
graphical models
high quality
image sequences
image segmentation
depth images
machine learning