Open fire opened 3 years ago
Hi, they are the same thing but in different representations.
Precisely speaking, our pose file is the joint rotation in rotation vector representation with the order of the name of the joint in the bvh file (i.e., joint named '00' appears first) plus root joint location. It has the shape of (number of frame, 24 * 3 + 3), where 24 indicate the number of joint and each joint takes 3 dimensions for rotation and the last 3 dimensions are for global location.
Ah. I recall some problems with vectors (eulers) versus basis.
I remember you choose basis (3x3 rot matrix) some time ago. Trying to check my understanding.
I use this representation here for a very simple reason: the dataset I used for training accepts this representation for joint rotations : ). In other part of the code it then is converted to 3x3 rot matrix for further uses.
How different is it from a skeletal transform representation of the animation on standard rig you chose?