What deep generative models can do with images

orig (6).png
The modern generative models take a latent code and generate a naturalistic image. These latent codes appear to have a natural geometry, and once we drag them, this induces meaningful image manipulation.
orig (2).gif
Images transformation after application of one of our methods.

First paper

orig (7).png
Some of the image transformations discovered by our method.

Second paper

orig (8).png
Some of the image manipulation achieved by a generative model weights change. Notably, some of them are unreachable by latent code shifts.

Third paper

orig (9).png
This picture shows how we generate saliency masks. The model allows us to synthesize a pair of images with the same content and a highlighted object on one of them. A simple color intensity comparison gives us the mask.

Conclusion