yhlscut / c4 Goto Github PK

There is no way to download the pre-training model

Hi, thank you for providing the code

How can I test other images or dataset from your model

Hi,the pretrained models can not download now， could you please share it once again，Thxs

Hello, when i use the GT illumination provided by you，i find that is the line transform from the real_illim_568.mat,
i want to know how is the Coefficient of variation，i,e. real_illu_568 / ? = GT

The input data's scale of pretrained model was [0 - 255], but in C4 the data was scaled to [0 -1].
Did you do it on purpose?

Hi, I would like to clarify the mismatch of performance on color checker (i.e., gehler) dataset I found in your paper. If I am wrong or misunderstand something, please correct me.

In your paper, I found that the reported mean angular errors of FC4 on the color checker dataset table are 2.40, while in the FC4 original paper, they report more lower mean angular errors, 1.65 (which is lower than your model 2.28). Also not to mention that there is also mismatch between your reported FFCC and the original one (since your paper does not clarify what type of FFCC you used, lets just focus on FC4).

I apologize if I misunderstand something, but the reported results seem to be problematic for me.
Could you please explain such performance mismatch? Thanks.

Woule you please update the download link, thanks very much

Hi,

Why do you convert the linear image to nonlinear image before sending data into network？

The link for the pretrained models is expired. Are there any other ways to get the pretrained model?