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

A Question about the 6DoF #75

Closed
wangzixing1998 opened this issue Feb 23, 2023 · 1 comment
Closed

A Question about the 6DoF #75

wangzixing1998 opened this issue Feb 23, 2023 · 1 comment
Labels
question Further information is requested

Comments

@wangzixing1998
Copy link

wangzixing1998 commented Feb 23, 2023

great job! However,In this code, I noticed that the projected box and image was scaled while training and inference, but nothing was done to the pose. I don't understand why. I would appreciate it if you can help me.

@vitoralbiero
Copy link
Owner

Hello @wangzixing1998,

So the pose doesn't need to be scaled, as what control the scale of it is the image intrinsics matrix, which is defined based on the image size.
Example, if you have an image 100x100, or 200x200, the pose will still be the same, only the intrinsics will need to be changed.
We do that when performing the calibration point loss, check here.

Hope this helps.

@vitoralbiero vitoralbiero added the question Further information is requested label Feb 24, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
question Further information is requested
Projects
None yet
Development

No branches or pull requests

2 participants