HybrIK
HybrIK copied to clipboard
Jeff-sjtu
3DPW data
Hello, thanks for the great work!
I tried to derive the same values as your 3DPW parsed data but I was unable to obtain the same values h36m_joints and smpl_joints.
I have a few questions: (1) What are your inputs into the SMPL and H36M regressor? (2) Was any translation applied? (3) How did you obtain the root coordinate?
With regards to (3), I've attached a screenshot of my outputs from h36m regressor. They differ from your g-t h36m_joints by an offset, which seems to be the "root coordinate". However, I'm unable to find this "root" from the original dataset. I was wondering how did you derive it? This is the same for your g-t smpl_joints
Hope to get your advice on this, thanks!
FYI, root_joint is either the first joint in SMPL or the average of left_hip and right_hip.
@wangzheallen Thanks for the reply! By "first joint in SMPL", do you mean the outputs from the SMPL regressor?
The first joint for my outputs from h36m regressor and smpl regressor were all zeros. However, in the author's provided g-t, the root joint of h36m_joints is [ 0.01080098 -0.25635168 0.0397297 ] and similarly, the root_joint of smpl_joints is [1.14881551 0.2267409 5.68205261], a non-zero value.
I can't seem to derive those root-joints or ground-truths for h36m_joints and smpl_joints from the raw 3DPW data. I was wondering if you have any idea on how to do that?
Hi @pangyyyyy, did you use the same h36m regressor as ours? As posted in #42, different regressors have slightly different joints.
@Jeff-sjtu I used the same h36m regressor. Unlike #43 , h36m_joints - h36m_joints root coordinate (I calculated) = h36m_joints - h36m_joints root coordinate (You provide) is the same.
However, my issue is that I am unable to obtain the exact h36m_joints root coordinate and smpl_joints root coordinate from your provided ground-truth. How did you obtain those root-coordinates from raw 3DPW data?
Hope to get your advice on this, thanks!