3D real-time single-person keypoint detection using 3D triangulation from multiple single views

Hzzone / pytorch-openpose

pytorch implementation of openpose including Hand and Body Pose Estimation.

2.03k stars 390 forks source link

3D real-time single-person keypoint detection using 3D triangulation from multiple single views #9

Closed JeremyKeusters closed 4 years ago

JeremyKeusters commented 4 years ago

I'm especially interested in the 3D real-time single-person keypoint detection using 3D triangulation which is available in the original OpenPose Caffe. I read in the README that you used caffemodel2pytorch for converting this code from Caffe. Could you maybe give some more details on this? So I could also convert the 3D triangulation code from the original repo?

Thanks in advance!

Hzzone commented 4 years ago

Model weights conversion has nothing to do with 3D triangulation. Firstly model inferences images from multi-veiw, and then does 3D triangulation according to detected keypoints.

JeremyKeusters commented 4 years ago

You're completely right, I'm sorry. Implemented it myself, thanks.