Is it necessary to train for motion reatarget
wuxiaolianggit opened this issue · 3 comments
The number of bone points is the same, but the proportion is not the same. I can directly copy the displacement and rotation vector of character a to the corresponding node of character B. in this way, the same effect can be achieved without using deep learning. Do you think my understanding is correct? @jimeiyang
If I understand correctly, you may be referring to the "Copy input quaternions and velocities" baseline in Table 1, and in the supplementary video. Please let me know if this is right.
Your understanding is correct, but I read your paper and found that the effect of hand reproduction is not very good. How do you think it should be improved? @jimeiyang
You can probably see in the paper that we do not handle full hands. We merely handle the joint named hand which does not include fingers. Therefore, hand is a leave joint and there is nothing really constraining it other than the twist term we use. If you want more accurate hand movements, I assume you would have to handle everything up to the fingers.