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

Can i apply this method on any image? #4

Open
wxxxxxxh opened this issue May 26, 2020 · 2 comments
Open

Can i apply this method on any image? #4

wxxxxxxh opened this issue May 26, 2020 · 2 comments

Comments

@wxxxxxxh
Copy link

Hi~
Can I adopt this method on any real world images directly? Such like some face images collected from net? I have tried it these days and i observe that your method may cause over-sharp problem. Can you give me some suggestion about this?
There is a couple of demos, i use the DPED.pth as the pretrained model.
LR:
Baidu_0000_1

SR:
Baidu_0000_1-SR

@jixiaozhong
Copy link
Owner

DPED model produces a sharp result due to the training image quality is quite low (To produce a sharp result). Maybe using DF2K model on this image will generate a not bad result. The over-sharp problem is more obvious with human face. Currently we are trying to train a specific model on human face data. It could take us some time...

@wxxxxxxh
Copy link
Author

Thanks for you reply. Look forward to your specific model on human face! And I will follow your advise
to try the DF2K model on my face data.

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