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

Why are the rotation axis of ZJU_MOCAP and wild different #86

Open
PolyLiYJ opened this issue Oct 31, 2023 · 2 comments
Open

Why are the rotation axis of ZJU_MOCAP and wild different #86

PolyLiYJ opened this issue Oct 31, 2023 · 2 comments

Comments

@PolyLiYJ
Copy link

I find that in the freeview.py, the rotation axes of different datasets are different. I wonder why are they different. Is the zju_mocap's world coordinates are different from the common-used one?

 ROT_CAM_PARAMS = {
        'zju_mocap': {'rotate_axis': 'z', 'inv_angle': True},
        'wild': {'rotate_axis': 'y', 'inv_angle': False}
    }
@Dipankar1997161
Copy link

yes. zjumocap normalises the smpl poses with the root joint

@sycamore27
Copy link

sycamore27 commented May 7, 2024

yes. zjumocap normalises the smpl poses with the root joint

But the prepare_wild.py file provided by the author also normalises the smpl poses with the root joint?

https://github.com/chungyiweng/humannerf/blob/c753322ae77d0abbf99f738277583da48478b91e/tools/prepare_wild/prepare_dataset.py#L75C9-L80C46

It seems not the reason why the zju_mocap's world coordinates are different. Do you know the other reason? Thanks very much! @Dipankar1997161 @PolyLiYJ

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