A dive into the different ways that Artificial Intelligence (AI) can and is being used in the VFX industry.
StyleGAN has recently established itself as one of the most prevalent approaches for image synthesis, generating images of phenomenal realism and fidelity. With its rich semantic space, many works have attempted to understand and control StyleGAN’s latent representations with the goal of performing image manipulations. To perform manipulations on real images, however, one must learn to “invert” the GAN and encode a given image into StyleGAN’s latent space, which remains an open challenge.
In this talk, we explore what makes StyleGAN such a fascinating case study. We begin by discussing recent techniques and advancements in GAN Inversion and explore their importance for real image editing applications. Then, going beyond inversion and image editing, we demonstrate how StyleGAN can be used for performing a wide range of image-to-image translation tasks.
SPEAKERS
Or Patashnik
Graduate Student // Tel Aviv University
Or Patashnik is a graduate student in the School of Computer Science at Tel Aviv University, under the supervision of Daniel Cohen-Or. Her research is about image generation tasks such as image-to-image translation, image editing, etc.
Website // Facebook // Instagram // Twitter
Yuval Alaluf
Graduate Student // Tel Aviv University
Yuval Alaluf is currently a graduate student studying Computer Science at Tel Aviv University. Under the supervision of Daniel Cohen-Or, his current research centers around various image generation applications including image editing, image-to-image translation, and more. Yuval's work has recently been featured on popular outlets such as TwoMinutePapers and Weights & Biases.
A dive into the different ways that Artificial Intelligence (AI) can and is being used in the VFX industry.
StyleGAN has recently established itself as one of the most prevalent approaches for image synthesis, generating images of phenomenal realism and fidelity. With its rich semantic space, many works have attempted to understand and control StyleGAN’s latent representations with the goal of performing image manipulations. To perform manipulations on real images, however, one must learn to “invert” the GAN and encode a given image into StyleGAN’s latent space, which remains an open challenge.
In this talk, we explore what makes StyleGAN such a fascinating case study. We begin by discussing recent techniques and advancements in GAN Inversion and explore their importance for real image editing applications. Then, going beyond inversion and image editing, we demonstrate how StyleGAN can be used for performing a wide range of image-to-image translation tasks.
SPEAKERS
Or Patashnik
Graduate Student // Tel Aviv University
Or Patashnik is a graduate student in the School of Computer Science at Tel Aviv University, under the supervision of Daniel Cohen-Or. Her research is about image generation tasks such as image-to-image translation, image editing, etc.
Website // Facebook // Instagram // Twitter
Yuval Alaluf
Graduate Student // Tel Aviv University
Yuval Alaluf is currently a graduate student studying Computer Science at Tel Aviv University. Under the supervision of Daniel Cohen-Or, his current research centers around various image generation applications including image editing, image-to-image translation, and more. Yuval's work has recently been featured on popular outlets such as TwoMinutePapers and Weights & Biases.
