Is it possible to run this model by providing depth maps and rgb video or previously computed keypoints?

rmbashirov / rgbd-kinect-pose

Demo for "Real-time RGBD-based Extended Body Pose Estimation" paper

MIT License

182 stars 22 forks source link

Is it possible to run this model by providing depth maps and rgb video or previously computed keypoints? #12

Open bs97 opened 1 year ago

bs97 commented 1 year ago

Hello,

I am interested in using this model for a research study, however, I am unable to run this model in real-time as I'm using a cluster for computation. Is it possible to use this model not in real-time e.g. by providing depth maps and video files, or by providing previously captured keypoints from azure skeletal tracking, minimalhand and mediapipe?

Any advice on this would be greatly appreciated.

dr00b commented 1 year ago

@bs97 please let me know what you discover here. I have a similar use case

felixshing commented 1 year ago

Similiar questions I have. did you find the solution?