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
First, thanks for your sharing. But these days, I had been confused by the usage of result_pose that described in the paper with 27 parameters. Would you please to help me figure out the order of result_pose? I'm really want to verify the effect of this algorithm in the 3D space.
The text was updated successfully, but these errors were encountered:
The 27 parameters represent global position and orientation as well as finger joint angles. The global position and orientation are encoded in the first 7 numbers (3 translation + 4 quaternion rotation). The rest correspond to joint angles for each finger joint. The base of each finger has two degrees of freedom while the rest have only one.
You can "decode" these numbers into 3D points in space using the corresponding decode functions (check the code for an example). For more info about the hand parameters check the Oikonomidis et al, BMVC11 paper.
First, thanks for your sharing. But these days, I had been confused by the usage of result_pose that described in the paper with 27 parameters. Would you please to help me figure out the order of result_pose? I'm really want to verify the effect of this algorithm in the 3D space.
The text was updated successfully, but these errors were encountered: