Unsupervised Projection Networks for Generative Adversarial Networks

Abstract

We propose the use of unsupervised learning to train projection networks that project onto the latent space of an already trained generator. We apply our method to a trained StyleGAN, and use our projection network to perform image super-resolution and clustering of images into semantically identifiable groups.

Publication
ICCV 2019: Sensing, Understanding and Synthesizing Humans

Related