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.
32 Commits
2 Branches
0 Tags
59 MiB
 
Tree: d4deb7eef1
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from 'd4deb7eef1'
${ noResults }
ViTPose/configs/body/3d_kpt_sview_rgb_img/pose_lift
Yufei 33f49cf1f2
register vitpose-b/l/h for coco 		3 years ago
..
h36m register vitpose-b/l/h for coco 3 years ago
mpi_inf_3dhp register vitpose-b/l/h for coco 3 years ago
README.md register vitpose-b/l/h for coco 3 years ago

README.md

A simple yet effective baseline for 3d human pose estimation

SimpleBaseline3D (ICCV'2017) 
@inproceedings{martinez_2017_3dbaseline,
  title={A simple yet effective baseline for 3d human pose estimation},
  author={Martinez, Julieta and Hossain, Rayat and Romero, Javier and Little, James J.},
  booktitle={ICCV},
  year={2017}
}

Simple 3D baseline proposes to break down the task of 3d human pose estimation into 2 stages: (1) Image → 2D pose (2) 2D pose → 3D pose.

The authors find that “lifting” ground truth 2D joint locations to 3D space is a task that can be solved with a low error rate. Based on the success of 2d human pose estimation, it directly "lifts" 2d joint locations to 3d space.