About Anna Fruehstueck Anna Fruehstueck Ph.D., Computer Science computer graphics visualization computational design procedural modeling machine learning image synthesis Anna Fruehstueck was a Ph. D. candidate under the supervision of Prof. Peter Wonka at King Abdullah University of Science and Technology (KAUST) and successfully defended her PhD in Computer Science on April 17, 2023. Education and Early Career Anna Fruehstueck obtained a Bachelor’s Degree in Media Informatics and Visual Computing from Vienna University of Technology in Austria in 2011. Later on in 2015, she received her M.Sc. degree in Visual Computing from Vienna University of Technology in Austria. During her studies, Anna worked as software developer at SimVis in Vienna, Austria. And in Events Presented Events Apr 16 - Apr 22, 2023 Latent Space Manipulation of GANs for Seamless Image Compositing Anna Fruehstueck, Ph.D., Computer Science Apr 17, 17:30 - 18:30 B5 L5 R5220 Generative Adversarial Networks image synthesis texture synthesis Generative Adversarial Networks (GANs) are a very successful method for high-quality image synthesis and are a powerful tool to generate realistic images by learning their visual properties from a dataset of exemplars. However, the controllability of the generator output still poses many challenges. In this thesis, we propose several methods for achieving larger and/or higher visual quality in GAN outputs by combining latent space manipulations with image compositing operations
Latent Space Manipulation of GANs for Seamless Image Compositing Anna Fruehstueck, Ph.D., Computer Science Apr 17, 17:30 - 18:30 B5 L5 R5220 Generative Adversarial Networks image synthesis texture synthesis Generative Adversarial Networks (GANs) are a very successful method for high-quality image synthesis and are a powerful tool to generate realistic images by learning their visual properties from a dataset of exemplars. However, the controllability of the generator output still poses many challenges. In this thesis, we propose several methods for achieving larger and/or higher visual quality in GAN outputs by combining latent space manipulations with image compositing operations
Engage ORCID ShareClipboard Related Sites Peter Wonka Research Group (P-Wonka) Computer Science (CS) Related Content Articles 2 Events 1 Related Links Also view list of Publications on KAUST Repository
