some question about the input image type

[TLcode001]

hello,I am very interested in your C5 work. But I have some doubts on the format of the input image. When I use my own dataset, should its data be 16-bit?，Is it ok if I directly enter a .hdr format? When the output is generated, what operations should be performed to get the feeling that accords with the human eye, such as CCM, AE and other operations？ Greatful thanks

[mahmoudnafifi]

Hi,

• Should its data be 16-bit? Though it is recommended to use 16-bit raw images, 8-bit raw images should be handled as well in the im2double function.
• Is it ok if I directly enter a .hdr format? You should first extract raw image data.
• What operations should be performed to get the feeling that accords with the human eye? This codebase does not include CCM/post-processing operations. It applies wb gains followed by a global gamma operator. If you have the 3x3 CCM values, then you should apply it before this line.

Hope you find this useful.

[TLcode001]

Hi, first of all, thanks for your answer, it's very helpful to me. Missed some questions last time

1. Our hdr data is 20bit, and the input data in your paper should be 16bit. Will this have any effect? Do we need to perform an automatic exposure operation on the hdr data first?