Hui Zeng

Hi, I have no idea on this problem :(

You may try to use the torch.nn.functional.grid_sample to replace the trilinear function if you have difficulty in building up the cuda implementation. Please refer to https://github.com/HuiZeng/Image-Adaptive-3DLUT/issues/14 for more information. It...

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...

11和2始终是等价的，但是一个LUT表达不了，w是一组随图像内容变化的权重。 可以在验证集上算指标观察训练过程，代码里应该有打印训练过程中的指标。

Hi， I also noticed this issue. This is a commom issue that many learning based image restoration or enhancement models have. That major reason may be that the model tend...

Hi, this sounds reasonable. But I have not tried it yet. You may update your findings if you make some attempts. Thanks.

For this purpose, you need to write some lines of code to read and process a set of images. You can check image_adaptive_lut_evaluation.py for reference.

Hi， thanks for sharing this code.

Hi, I has been several years that I did not work on the IQA topic. If I remember correctly, the variance is very large when using different random splits. That...

Hello. I'm sorry that I have no experience of transforming DMOS to MOS :(