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.
30 Commits
2 Branches
0 Tags
59 MiB
 
Tree: 54a546bab9
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from '54a546bab9'
${ noResults }
ViTPose/configs/face/2d_kpt_sview_rgb_img/topdown_heatmap
Yufei 33f49cf1f2
register vitpose-b/l/h for coco 		3 years ago
..
300w register vitpose-b/l/h for coco 3 years ago
aflw register vitpose-b/l/h for coco 3 years ago
coco_wholebody_face register vitpose-b/l/h for coco 3 years ago
cofw register vitpose-b/l/h for coco 3 years ago
wflw register vitpose-b/l/h for coco 3 years ago
README.md register vitpose-b/l/h for coco 3 years ago

README.md

Top-down heatmap-based face keypoint estimation

Top-down methods divide the task into two stages: face detection and face keypoint estimation.

They perform face detection first, followed by face keypoint estimation given face bounding boxes. Instead of estimating keypoint coordinates directly, the pose estimator will produce heatmaps which represent the likelihood of being a keypoint.

Various neural network models have been proposed for better performance. The popular ones include HRNetv2.