Masterclass in Visual Computing
Abstract
In this talk, Professor Peter Wonka will review multiple applications that have been enabled by the state-of-the-art generative adversarial network called StyleGAN. Given a single input image, a user can perform semantic manipulations that require prior knowledge of the depicted scene or object. This prior knowledge is encoded in the StyleGAN framework to enable image manipulation of unprecedented quality. Applications include the editing of single photographs for the virtual try-on of cloths, transfer of hairstyles, editing of a person's age, image colorization, or image superresolution.
Brief Biography
Peter Wonka is a Full Professor in Computer Science at King Abdullah University of Science and Technology (KAUST) and Associate Director of the Visual Computing Center (VCC). Peter Wonka received his doctorate from the Technical University of Vienna in computer science. Additionally, he received a Masters of Science in Urban Planning from the same institution. After his Ph.D., Dr. Wonka worked as a postdoctoral researcher at the Georgia Institute of Technology and as faculty at Arizona State University. His research publications tackle various topics in computer graphics, computer vision, remote sensing, image processing, visualization, and machine learning. The current research focus is on deep learning, generative models, and 3D shape analysis and reconstruction.
Related Persons
