search

mks0601 / 3DMPPE_POSENET_RELEASE

Official PyTorch implementation of "Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image", ICCV 2019
MIT License
807 stars 147 forks source link

About R and t in h36m #100

Closed pangyyyyy closed 2 years ago

pangyyyyy commented 2 years ago

How did you obtain the camera parameters R, t, f, c in H36M parsed data? I've tried to derive the camera parameters from metadata.XML provided in the H36M website but I got a different t from the ones in your annotation file.

P.S. I was referred to here by https://github.com/Jeff-sjtu/HybrIK/issues/46

mks0601 commented 2 years ago

I think what you got it T, and mine is -np.dot(R, T.reshape(3,1)).reshape(3)

pangyyyyy commented 2 years ago

I see, thanks for the clarification!