FeMaSR
FeMaSR copied to clipboard
PyTorch codes for "Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priors", ACM MM2022 (Oral)
I am very impressed with your project and upscale models. Tried project in google colab and results are fascinanting, even better than commercial products. Cause I have AMD radeon GPU,...
I am trying to reproduce the code visualization part of your paper, and successfully generate reconstructed texture under the single code cases., which I referred to this code snippet: ![image](https://user-images.githubusercontent.com/32531785/167557638-45cba07b-11a7-4de3-a466-efd0d702822b.png)...
Hi there, I cannot train the network and converge to the numeric metric values reported in the manuscript in the SR stage. All settings and experiments are performed for x4...
Thanks for sharing your code. The results I get after training have obvious signs of fragmentation. Do you have any improvement suggest?training 60 epochs, but indicators such as psnr did...
Hello author, your article has inspired me a lot. I am currently reproducing your paper, but the dataset creation method of this paper is very difficult for me, if you...