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

"kornia.geometry.transform.warp_perspective" #1

Open
cuishuhao opened this issue Mar 10, 2022 · 2 comments
Open

"kornia.geometry.transform.warp_perspective" #1

cuishuhao opened this issue Mar 10, 2022 · 2 comments

Comments

@cuishuhao
Copy link

Thanks for sharing the excellent job!
In achieving STN, instead of the pytorch tutorials of STN, the codes adopt "kornia.geometry.transform.warp_perspective" to generate new images.
I wonder why kornia is adopted, and the differences between the methods.

@charigyang
Copy link
Owner

Hi, thanks for the interest in our work.

The tutorial mentioned might be this one? https://pytorch.org/tutorials/intermediate/spatial_transformer_tutorial.html

It should be very similar -- given that warp_perspective is based on grid sample anyway. The only difference here is we do perspective warping as opposed to affine in the original STN, but I don't think that will make a major difference in terms of outcome.

@cuishuhao
Copy link
Author

Thank you!

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

2 participants