How can I get the coordinate of body keypoints with GFPose when input a video?

Embracing / GFPose

Official implementation for the CVPR2023 paper: "GFPose: Learning 3D Human Pose Prior with Gradient Fields"

Apache License 2.0

123 stars 5 forks source link

How can I get the coordinate of body keypoints with GFPose when input a video? #8

Closed wxl81315 closed 4 months ago

Embracing commented 4 months ago

You may need to run a 2D pose estimator first to get 2D keypoints for each frame. Then run GFPose on each frame to get the corresponding 3D keypoints. Note that 2d keypoints must follow the H36M format.