search

mkocabas / EpipolarPose

Self-Supervised Learning of 3D Human Pose using Multi-view Geometry (CVPR2019)
Other
597 stars 97 forks source link

About the triangulation algorithm #19

Closed StatML closed 5 years ago

StatML commented 5 years ago

Hi, @mkocabas Thanks for sharing your wonderful project! I have a question about triangulation. To my knowledge, both the camera rotation and translation parameters are needed to use the polynomial triangulation algorithm. But it seems your paper did not tell how to derive the camera translation parameters, and your codes do not show how to call the function polynomial_triangulation. Can you share some experience or supplement some demo of calling polynomial_triangulation? Thx a lot!

mkocabas commented 5 years ago

Hi @StatML,

Thanks for your interest.

To my knowledge, both the camera rotation and translation parameters are needed to use the polynomial triangulation algorithm.

Yes, you are right we need camera parameters to perform triangulation. But one can use predicted human pose as the calibration target to obtain rotation and translation of the cameras. Note that translation is up to a scale.

But it seems your paper did not tell how to derive the camera translation parameters

Not really, we explain it in detail in section 3.1 4th paragraph in the paper. Please refer to that section.

your codes do not show how to call the function polynomial_triangulation.

You are right, I will update the repo soon. Please refer to my reply in issue https://github.com/mkocabas/EpipolarPose/issues/18.

Best,

ericzw commented 5 years ago

@mkocabas Hi, I met the same problem. I want to know how to use the function polynomial_triangulation. Can you give us more details?