S M A Sharif

Can you please explain your points? I could not figure it out.

Hi there, Thanks for pointing out such an important issue. I crossed checked the implementation, it seems like the calculated loss with permutation and reshaping functions are identical. However, we...

Thanks for your insightful analysis. You're absolutely right. During training, we read all images with PIL. Also, we leveraged tanh in the final layer of our model. Thus, generated and...

Hi there! Thanks for raising such an important issue. Our previously shared weight files were corrupted. However, we have updated the weight files. Here are some sample images obtained from...

As you pointed out, we did not perform any retraining of our model after submitting the paper. I guess it would be unfair and unethical to upload a newly trained...

Thanks for your query. Please have a look: https://github.com/sharif-apu/BJDD_CVPR21/issues/4#issuecomment-1116341389

Hi There! Sorry for the late response. align_ratio indicates the normalization value for reverting the original range of images. We may find it along with the training samples. For more...

Thanks for your query and sorry for the late response. First of all, our research group focuses on computer vision and image processing. Regrettably, we are not experts in display...