Closed yinnhao closed 2 years ago
@hahahaprince Actually the mask is calculated from the original SDR image. I generete the masks of the input SDR images in mask_folder in advance then read the masks from the mask folder.
@hahahaprince It seems an error in the released version, I have just corrected it.
Okay, I get it. Thanks
Hi, thank you for your great work! I have some question about the mask calculation in highlight generation. As discribed in Figure 2 in your paper, the mask is computed from original SDR image, but I found it is computed from LE output in your code. So which one should we use? As I realized, the non-linear RGB value in HDR image is hardly more than 0.95.
https://github.com/chxy95/HDRTVNet/blob/41d63b58bb953a83fcd1666d77848945a261fb06/codes/data/LQGT_hallucination_dataset.py#L77