root_orientation for KIT dataset

[saneeeee]

Hello, it is mentioned in #2 that ["poses"][:, :3] gives the orientation of the root joint in the global frame. However, for KIT/425/walking_slow09_poses.npz (a basic walking forward without rotating) these entries correspond to the following plot.

I'm struggling to make sense of these root_orient entries as there is ~15deg rotational range in all 3 axes although the render depicts minimal rotation. Moreover, I can't make sense of nonzero pitch and yaw.

Is this an error with the KIT dataset or I am following a flawed method to extract roll,pitch,yaw of the root joint? If so could you please point out the correct way to extract rpy, thanks!

[saneeeee]

I noticed that the same issue persists for CMU dataset, for example 02_01 yields rotations:

Although the video shows minimal roll/pitch/yaw.

This notebook mentions "The global root orientation of amass is so that if you render with MeshViewer you will always get a top view of the body. One can rotate the body into front view by transforming the mesh." I think this would explain a constant offset in rotations, but I still can't justify the fluctuations.