You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The visualization of the 3D keypoints for a multihuman dataset is producing keypoints below the z=0 as shown in the image below. This is due to having -ve values in the z-coordinate of the 3D keypoints. Is this an expected behaviour or does this mean there is an error in the predictions of the 3D keypoints? If there is an error, what could be the reason?
The text was updated successfully, but these errors were encountered:
The dataset is already pre-calibrated in advance, so I have no control over the calibration parameters. I guess it was generated while assuming that the ground is not at z=0.
The visualization of the 3D keypoints for a multihuman dataset is producing keypoints below the z=0 as shown in the image below. This is due to having -ve values in the z-coordinate of the 3D keypoints. Is this an expected behaviour or does this mean there is an error in the predictions of the 3D keypoints? If there is an error, what could be the reason?
The text was updated successfully, but these errors were encountered: