Usage on 2D images

[astammer]

Hello,

In you paper you had mentioned, that you have used ViT-AE++ on 3D as well as 2D images. However the ViT and autoencoder seem to be specifically written for 3D Images.
Could you hint me into the right direction, of how I could use this autoencoder on 2D images? Or was a separate code used for this?

Thank you in advance for your help!