Open Tengoles opened 1 year ago
Hi @Tengoles, camera_root
is the root position in the camera coordinates. But the SMPL model will add a default offset to the root joint after both forward kinematics and inverse kinematics. Therefore, we use the term transl
which considers the default offset. cam_trans
and cam_scale
are used for training. Following HMR, cam_trans
is related to tx
and ty
, and cam_scale
is the scale term.
the SMPL model will add a default offset to the root joint after both forward kinematics and inverse kinematics
Could you provide the line of this operation?
Hello! wanted to get some clarification on what is the relationship between the pose_output parameters mentioned in the title. I know they are all related with the world coordinates, camera coordinates and root position of the body but not sure exactly how.