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

Exporting 3d pose to animation in unity or blender ? [extension] #4

Closed
ns3new opened this issue Aug 29, 2019 · 5 comments
Closed

Exporting 3d pose to animation in unity or blender ? [extension] #4

ns3new opened this issue Aug 29, 2019 · 5 comments

Comments

@ns3new
Copy link

ns3new commented Aug 29, 2019

Hi
I was wondering if there is a script , that parses out the 3d joints per frame , that can be used for animation purposes or perhaps there is an already exisitng module that does that ?
/Thanks
N

@zh-plus
Copy link
Owner

zh-plus commented Aug 29, 2019

There's a visualization function invoked here, which generate the animation using matplotlib. However, unity or blender animation is not provided.

On the other way, you can save the predicted 3d pose (in numpy array format) after here where the post-process has been done. And then convert them into the specific(unity or blender) format by your self.

Contributions of the visualization module are welcomed.

@zh-plus zh-plus closed this as completed Sep 7, 2019
@ns3new
Copy link
Author

ns3new commented Dec 3, 2019

Can i ask you what does this line of code do ??

rot = np.array([0.14070565, -0.15007018, -0.7552408, 0.62232804], dtype=np.float32)

Thanks!

@zh-plus
Copy link
Owner

zh-plus commented Dec 3, 2019

Rotation part of the extrinsic parameter in 2d scenario, which is used to convert the prediction from camera space into world space. Check out this for more information about the camera parameters.

@ns3new
Copy link
Author

ns3new commented Dec 4, 2019

Thank you !

@krunal-jain
Copy link

On the other way, you can save the predicted 3d pose (in numpy array format) after here where the post-process has been done. And then convert them into the specific(unity or blender) format by your self.

As mentioned, I am trying to save predictions in npy file. It would be helpful if you can verify that these predictions are in [x,y,z] order @zh-plus

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

3 participants