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

bad results, not much improvment over AMT #1

Open
eisneim opened this issue Jun 21, 2024 · 4 comments
Open

bad results, not much improvment over AMT #1

eisneim opened this issue Jun 21, 2024 · 4 comments

Comments

@eisneim
Copy link

eisneim commented Jun 21, 2024

hi thanks for sharing this work!
but after some experiments, the interpolation result is not good, any advice on how to get the best result?

method: raft+pervfi scale 4

seq_backflip-raft+pervfi.mp4
seq_flip2-raft+pervfi.mp4

0000075
0000027

still waiting for vidim this paper seems good at interpolate large motion

@eisneim
Copy link
Author

eisneim commented Jun 21, 2024

comparing with MoMo which uses Diffusion model when creating in between frames, MoMo does better job

4x-.mp4

@tkkcc
Copy link

tkkcc commented Jun 28, 2024

Hi, would you like to share your input video.

@eisneim
Copy link
Author

eisneim commented Jun 29, 2024

@mulns
Copy link
Owner

mulns commented Jul 4, 2024

Currently, we only release model for scale X2. The model trained for X4 and X8 interpolation is under preparation

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