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

Extra options or more advanced updated DFDNet branch / project ? #71

Open
AlonDan opened this issue Apr 6, 2021 · 2 comments
Open

Extra options or more advanced updated DFDNet branch / project ? #71

AlonDan opened this issue Apr 6, 2021 · 2 comments

Comments

@AlonDan
Copy link

AlonDan commented Apr 6, 2021

I'm wondering if there is a more up to date DFDNet branch or similar project that can:

1. Show progress bar with estimate time while process of the different tasks (Crop and Align, Face Landmark Detection, Face Restoration, Past) ?

2. Work on FULL IMAGE and not just the face?

3. Are there any upcoming new improvement from the last update of DFDNet, on similar projects out there that already improved?

Sorry but I'm new to this, I found DFDNet amazing and I wonder if there are upcoming improvements or maybe already there are either as different unofficial branches or totally different project like it, so if anyone can share or recommend with some links?

Thanks ahead!

@ivellios1988
Copy link

Well, if you want to enhance whole image then you will need to use more than one tool, as there is no GAN that would be capable of enhancing the whole image. As far as I know, GANs that are currently available are trained to generate or enhance particular types of content. For example, if a GAN is trained to enhance faces, it will only enhance faces and nothing more. When the algorithm encounters elements it doesn't 'know' then it leaves them unchanged.

There are some AI tools available that you might find interesting. Topaz Labs applications perform amazing job with upscaling, sharpening and denoising images. There's also Let's Enhance https://letsenhance.io with tool called 'Smart Enhance' that is capable of enhancing whole images by reducing pixelation, sharpening, etc.

Use these tools along with DFDNet (or Remini or whatever face-enhancing software you like) and you'll achieve almost pixel-perfect portraits :)

@JoeyStrandnes
Copy link

I'm also interested in enhanced features!

Regarding your interest in status like a progress bar.
"Show progress bar with estimate time while process of the different tasks (Crop and Align, Face Landmark Detection, Face Restoration, Past) ?"

I was interested in the same thing so I created a very simple GUI that shows the progress of the of the enhancement and adds some other functionality like processing input images in batches.
I'm working on adding more status information but it works well as of writing.

Might be of use to you?

GitHub project

GitHub release

Demo

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