I have a question. The paper said that interfaceGAN was used when manipulating latent code. Is it correct to use interfaceGAN when dealing with the tower dataset instead of the face dataset?
I know that interfaceGAN has been experimented with only the face dataset.
Yes, InterfaceGAN can be used to find the editing directions. However, you need some classifiers trained on the scene (e.g., Places) to obtain your expected direction.
Thank you for your great work.
I have a question. The paper said that interfaceGAN was used when manipulating latent code. Is it correct to use interfaceGAN when dealing with the tower dataset instead of the face dataset?
I know that interfaceGAN has been experimented with only the face dataset.