You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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
The text was updated successfully, but these errors were encountered:
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.
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
The text was updated successfully, but these errors were encountered: