about preprocessing of the input image

[SHMCU]

Hi Mahmoud,

Thanks for sharing the great work!
May I know whether there is some preprocessing to the images input to the network. Here is what I observed, when the input is from the ffcc's dataset: https://github.com/google/ffcc/tree/master/data
the output looks good. But if input other data like NUS from here: http://cvil.eecs.yorku.ca/projects/public_html/illuminant/illuminant.html
the output is bad. Is this because I missed some preprocessing steps?

Thanks
Simon

[mahmoudnafifi]

Hi Simon,

Yes, the image should be normalized using the black-level and saturation-level values. You can either find these values in the DNG metadata or from the dataset provider (for example in the NUS dataset those values are given from each camera). Then, each image should be normalized as follows: normalized_image = (image - black_level) / (saturation_level - black_level)

I hope this helps.