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
Hello, I have another question:
I download the preprocessed SnapshotPeople dataset provided in the link, and I test it using the male-3-casual sample. We use the data from InstantAvatar and finetuned their pre-processed poses to get SMPL-X fits.
First, I decode the 000.pkl file in the smplx_finetune/result directory, and I notice that the shapes of left_hand_pose and right_hand_pose are both (1, 12). However, theoretically, the left_hand_pose/right_hand_pose outputs of SMPL-X are typically (15, 3). I understand that enabling the parameter num_pca_comps=12 reduces the hand pose dimension from 15 to 12, but why is the other dimension 1 instead of 3?
The text was updated successfully, but these errors were encountered:
Hello, I have another question:
I download the preprocessed SnapshotPeople dataset provided in the link, and I test it using the
male-3-casual
sample.We use the data from InstantAvatar and finetuned their pre-processed poses to get SMPL-X fits.
First, I decode the
000.pkl
file in thesmplx_finetune/result
directory, and I notice that the shapes ofleft_hand_pose
andright_hand_pose
are both(1, 12)
. However, theoretically, theleft_hand_pose
/right_hand_pose
outputs of SMPL-X are typically(15, 3)
. I understand that enabling the parameternum_pca_comps=12
reduces the hand pose dimension from 15 to 12, but why is the other dimension 1 instead of 3?The text was updated successfully, but these errors were encountered: