For tone-mapping task, why did you use the expertC as the GT?

[Jian-danai]

Hi, in your paper, you said "It should be noted that we only learn the color/tone enhancement part of the imaging pipeline rather than learning the entire pipeline from raw data to final RGB output." But in your XYZ image dataloader, you used expertC as the GT rather than the tone-mapped (gamma corrected) images (i.e. the input images in your photo retouching task). In this way, you did both tone-mapping and photo retouching task. Could you explain why?