TAU Style: inversion, editing, and applications of StyleGAN. Dr. Amit Bermano from Tel-Aviv University (CS Colloquium)

(CS Colloquium)

TAU Style: inversion, editing, and applications of StyleGAN.

Dr. Amit Bermano

Tel-Aviv University 

Abstract: 

The generative abilities of GANs are revolutionizing the field of image synthesis and manipulation.

Specifically, StyleGAN reaches the highest levels of image quality, and has become the de-facto golden standard for the editing of facial images.

StyleGAN is unsupervised, and yet its latent space is surprisingly well behaved. In this talk I will briefly introduce this concept, the generator, and how it works.

Through a line of publications, I will present  how to use StyleGAN with real images (also known as inversion), how to alter a facial image in novel ways (using latent-space editing),

how to harness it’s powers for domains with sparse, or even no, training examples, and how our lab has contributed to StyleGAN’s phenomenal success story.

Bio:
 Dr. Amit H. Bermano is a senior lecturer (assistant professor) at the Blavatnik School of Computer Science in Tel-Aviv University since 2018. His research focuses on Computer Graphics, Computer Vision, and Computational Fabrication, using tools from Machine Learning and Geometry Processing. Previously, he was a postdoctoral Researcher at the Princeton Graphics Group, and a postdoctoral researcher at Disney Research Zurich. He has conducted his doctoral studies at ETH Zurich, in collaboration with the computational materials group of Disney Research Zurich. His Masters and Bachelors degrees were obtained at The Technion – Israel Institute of Technology.