InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs

Understand

Although Generative Adversarial Networks (GANs) have made significant progress in face synthesis, there lacks enough understanding of what GANs have learned in the latent representation to map a random code to a photo-realistic image.

• In this work, we propose a framework called InterFaceGAN to interpret the disentangled face representation learned by the state-of-the-art GAN models and study the properties of the facial semantics encoded in the latent space.
• We first find that GANs learn various semantics in some linear subspaces of the latent space.
• After identifying these subspaces, we can realistically manipulate the corresponding facial attributes without retraining the model.