8000 question on image representation results · Issue #10 · vishwa91/wire · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

question on image representation results #10

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.

Sign up for GitHub

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

Jump to bottom
Open
jypppppp opened this issue Jun 27, 2023 · 4 comments
Open

question on image representation results #10

jypppppp opened this issue Jun 27, 2023 · 4 comments

Comments

@jypppppp
Copy link

Dear author,

When I redo the image representation on the "lighthouse" image, the result is 25 dB which is a big difference from 43.2 dB and the time is around 3 min. I run it on "wire_occupancy.py" and changed layer numbers to 3 and neuron numbers to 300.

Is what I did right?

Thank you

Jason
@vishwa91
Copy link
Owner

Thank you for the question. Two changes to replicate the result:

  1. Downsample image by 1/4 -- this is to ensure that the number of parameters in the network, and image complexity (pixels) is similar.
  2. Set omega=20, and sigma=20 -- as we discussed in the paper, the set of (omega, sigma) for image representation and image denoising are different. Intuitively, for representation, we want higher frequencies overall, and hence larger omega, sigma.

Hope that helps!

@jypppppp
Copy link
Author
jypppppp commented Jul 5, 2023

Thanks for your reply and it helps a lot.

Also, can you provide the code for single image super-resolution?

Jason

@vishwa91
Copy link
Owner
7E51
vishwa91 commented Jul 5, 2023

Will upload SISR code within a week!

@KexuanShi
Copy link

I found an interesting phenomenon that when the 1e-4 learning rate was used, the output of models can't accurately represent the color of the image. But with the 5e-3 learning rate , there is no problem. Even the small learning rate has the same psnr with large learning rate

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@vishwa91 @jypppppp @KexuanShi
0