As far as I know, to evaluate synthesized images it is proposed to use:

  • human scoring,
  • "Inception score",

where in the second case the quality is rated based on a pre-trained Inception model’s ability to classify them.

I find "Inception score" method rather complex, but that's not the point. Is there any other method to evaluate synthesized images? For example, calculating RMSE of the result and ground truth images, or something like that.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.