fhw
/
ViTPose
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
33 Commits
2 Branches
0 Tags
59 MiB
 
Tree: 0eb96d2c47
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from '0eb96d2c47'
${ noResults }
ViTPose/configs/body/3d_kpt_sview_rgb_vid
Yufei 33f49cf1f2
register vitpose-b/l/h for coco 		3 years ago
..
video_pose_lift register vitpose-b/l/h for coco 3 years ago
README.md register vitpose-b/l/h for coco 3 years ago

README.md

Video-based Single-view 3D Human Body Pose Estimation

Video-based 3D pose estimation is the detection and analysis of X, Y, Z coordinates of human body joints from a sequence of RGB images. For single-person 3D pose estimation from a monocular camera, existing works can be classified into three categories: (1) from 2D poses to 3D poses (2D-to-3D pose lifting) (2) jointly learning 2D and 3D poses, and (3) directly regressing 3D poses from images.

Data preparation

Please follow DATA Preparation to prepare data.