HuiZeng / Image-Adaptive-3DLUT

Learning Image-adaptive 3D Lookup Tables for High Performance Photo Enhancement in Real-time

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

About UIE [11]

yyrkoon27 opened this issue · comments

Good day, Dr. Zeng,

Thanks for your great work. Here I have some questions about UIE [11] as cited in your paper.

  1. It actually doesn't iteratively enhance the input image. It runs the forward pass once for each input image. You can check its description in the section "Generator" in [11].
  2. About the running time, the slow speed of UIE should be related to the fact that it reproduces those Adobe Lightroom adjustments in Python, which might not be GPU-friendly. In any case, its speed should have nothing to do with its number of iterations, as mentioned in your paper in Sec. 4.6.

Please see if I miss something in your arguments. All in all, the above won't change much about your work's value. However, the discussion here is to view things more objectively and correctly.

Thanks for your attention :-)

Hi, thanks for your clarification and sorry for the inappropriate explanation in the paper.
Since the paper has been accepted and cannot be modified again, I will keep this issue open to let more people see your clarification.