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

About video hair removing #23

Open
Dratlan opened this issue Jul 16, 2024 · 7 comments
Open

About video hair removing #23

Dratlan opened this issue Jul 16, 2024 · 7 comments

Comments

@Dratlan
Copy link

Dratlan commented Jul 16, 2024

I've tried this code for video hair removing, the results is not so good(with flicker and discontinuities). Do you have some suggestions?

@oneThousand1000
Copy link
Owner

Maybe transferring our method to 3D-aware model could be helpful (but it needs some experiments and algorithm design, it's not straightforward and easy)

@Dratlan
Copy link
Author

Dratlan commented Jul 22, 2024

Thanks for your suggestions, I'll try for it

@Dratlan
Copy link
Author

Dratlan commented Jul 22, 2024

微信图片_20240722161134
and another question In Fig.5, how can I get blended image(bottom right) from synthetic image(bottom middle)? the blurring mask around the face is not needed for me.

@oneThousand1000
Copy link
Owner

The Blending is based on Poisson Editing

@Dratlan
Copy link
Author

Dratlan commented Jul 22, 2024

Thanks, is there a code implementation in this repository?

@oneThousand1000
Copy link
Owner

Thanks, is there a code implementation in this repository?

mixed_clone = cv2.seamlessClone(origin_img, res_img[:, :, ::-1], face_mask[:, :, 0], center,

@Dratlan
Copy link
Author

Dratlan commented Jul 22, 2024

Thanks for your quickly reply

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