Juheon Yi

@nmber5 Hi, I am facing the same issue here (the LR face generated by my code is different from the LR faces provided in the author's repo. Did you find...

@samehraban Hi, did you manage to prepare the training data successfully? Could you share how you managed it? Thanks!

Hi, sorry for the terrible delay. Haven't been able to keep track of this repo for a long time, as I had other projects I needed to focus on :(...

Sorry for the late response. To be precise, I think the texture loss should be as how you pointed out, same as the original GAN paper. Though, I think my...

Hi, sorry for the terrible delay. Haven't been able to keep track of this repo for a long time, as I had other projects I needed to focus on :(...

Thanks for the constructive comment! Additional loss term to enforce the enhanced image to have different color distribution seems a nice idea. I think it would be stronger if we...

Hello, thanks for the attention. Please refer to the notebook files (ESPCN.ipynb, VESPCN.ipynb) for running the codes. Also, please note that current implementation of VESPCN is not complete. I am...

Hello, thanks for paying attention to my codes. Unfortunately, I am still in progress of updating the code to a newer version. As of the old version implementation I previously...

Hello, sorry for the terrible delay. I missed the issue you left. From what I understand, equation (5) in section 2.3 means that the pixel value at (x,y) in transformed...

Hi, were you able to fully reproduce the validation results with the fix? Even after applying the scale correctly, there are still some difference...