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

Step of demosaicing #9

Closed
xunmeibuyue opened this issue Oct 8, 2021 · 3 comments
Closed

Step of demosaicing #9

xunmeibuyue opened this issue Oct 8, 2021 · 3 comments

Comments

@xunmeibuyue
Copy link

Hi Yazhou,

An excellent work!

I notice that you use bilinear demosaicing by Python library colour_demosaicing, and I guess it is aiming to reverse this step. However, I wonder would if bilinear demosaicing would be enough for an ISP? It seems to have some disadvantages, such as colour error and blurring. Did you notice this problem?

Best,
Kenneth

@yzxing87
Copy link
Owner

yzxing87 commented Oct 8, 2021

Hi Kenneth,

Yes, we use bilinear demosaicing since it is invertible. And I admit that bilinear demosaicing is so simple that it may not fit for some advanced ISPs. But in our method, our model can optimize the output RGB towards the ground truth, whose demosaicing is more complicated that bilinear demosaicing. So it should not be a problem in our pipeline.

Actually we found there is a bug in colour_demosaicing, which may cause the color error for the RGB output. And we should note that the results in our paper are correct (after fixing the bug). We may post the fixing method in readme.

@xunmeibuyue
Copy link
Author

Get it.

And maybe you could create a pull request to colour_demosaicing? That would be a meaningful contribution~

Anyway, thanks!

@yzxing87
Copy link
Owner

yzxing87 commented Oct 8, 2021

Thanks, Kenneth. Will do.

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