New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

can I use PatchSWD for AutoEncoder reconstruction? #3

Open

iperov opened this issue Apr 28, 2023 · 1 comment

iperov commented Apr 28, 2023

Thanks for your work.

can I use this loss for AutoEncoder reconstruction?

Currently I am using multiple patch sizes in order to get more GAN-like patterns of reconstruction.

Are there any additional approaches to get better quality?

Owner

ariel415el commented May 7, 2023

Sure you can. I tried this too but it does not seem to be comparable to GAN

The results looks somewhat similar to MMD++ here https://github.com/ariel415el/PerceptualLossExperiments#5-generative-models

If interested you can read this paper that analyzes patch distribution losses and tests them in super-rseolution setting

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment