search

greatlog / DAN

This is an official implementation of Unfolding the Alternating Optimization for Blind Super Resolution
231 stars 41 forks source link

The SSIM is much lower #15

Closed zejinwang closed 3 years ago

zejinwang commented 3 years ago

I have generated the test dataset according to the test setting1 and test the provided pre-trained model on it. The PNSR results are roughly the same as you have mentioned in Table 1. However, the SSIM is much lower. Could tell me how to solve this issue.

greatlog commented 3 years ago

It seems to be a bug in the older version of IKC. The reported SSIM results of IKC and our models on Setting 1 are wrong. Probably the SSIM results in Table 1 are all wrong. While the authors of IKC do not provide any explanations, I will correct these results according to my re-implementation. The corrected results will de updated soon.

zejinwang commented 3 years ago

It seems to be a bug in the older version of IKC. The reported SSIM results of IKC and our models on Setting 1 are wrong. Probably the SSIM results in Table 1 are all wrong. While the authors of IKC do not provide any explanations, I will correct these results according to my re-implementation. The corrected results will de updated soon.

Thanks for your quick and detailed reply. I got it.