ECCV 2020 paper

StyleGAN2 Distillation for
Feed-forward Image Manipulation

TL;DR

Paired image-to-image translation, trained on synthetic data generated by StyleGAN2 outperforms existing approaches in image manipulation.

Abstract

StyleGAN2 is a state-of-the-art network in generating realistic images. Besides, it was explicitly trained to have disentangled directions in latent space, which allows efficient image manipulation by varying latent factors. Editing existing images requires embedding a given image into the latent space of StyleGAN2. Latent code optimization via backpropagation is commonly used for qualitative embedding of real world images, although it is prohibitively slow for many applications. We propose a way to distill a particular image manipulation of StyleGAN2 into image-to-image network trained in paired way. The resulting pipeline is an alternative to existing GANs, trained on unpaired data. We provide results of human faces’ transformation: gender swap, aging/rejuvenation, style transfer and image morphing. We show that the quality of generation using our method is comparable to StyleGAN2 backpropagation and current state-of-the-art methods in these particular tasks.

One-minute video

ECCV 2020 poster video

Results

Authors

Cookie files
Yandex uses cookies to personalize its services. By continuing to use this site, you agree to this cookie usage. You can learn more about cookies and how your data is processed in the Privacy Policy.
Fri May 21 2021 17:38:30 GMT+0300 (Moscow Standard Time)