Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Retargeted animation looks really weird (upperArm position)... Is that normal? #63

Open
nicolasfischoeder opened this issue Sep 29, 2023 · 3 comments

Comments

@nicolasfischoeder
Copy link

Hello everybody,

I am attempting to retarget one of my own animations onto AMP via the provided scripts. However, I notice that the upper arm/shoulder positions look very off compared to my t-Pose and original animation. Basically they have the same height as the highest point in my skeleton, which I assume to be the head-bone.

Screenshots:

  1. Retargeted animation
  2. My rig t-pose in the fbx-importer
  3. My animation in the fbx-importer

Screenshot from 2023-09-29 16-02-20
Screenshot from 2023-09-29 16-06-21
Screenshot from 2023-09-29 16-07-11

What strikes me the most is, that the retargeting from the CMU examples produces the identical behavior!

@xbpeng Can you please comment on that? What is the deal here? Can you maybe provide a screenshot of the reallusion retargeting? What would you recommend?

@xbpeng
Copy link
Collaborator

xbpeng commented Oct 2, 2023

hard to tell what's going on here. It almost seems like the retargeted results are completely ignore the pose in the source data? You'll probably need to dig into this a bit to see what might be going wrong.

@YandongJi
Copy link

Having the same issue, seems like when the two architectures are too different, the skeleton will also change

@hhebb
Copy link

hhebb commented Oct 4, 2023

i have encountered same issue.

one possible solution that i am using.

  1. retarget your motion -> cmu t-pose
  2. retarget cmu motion -> amp t-pose (as introduced in motion_lib example)

i successfully using my motion using this mehod.

good luck

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

4 participants