Natural Language Models For Unnatural Languages Wamiq Para, Ph.D. Student, Computer Science Nov 20, 14:00 - 16:00 B1 L2 R2202 Generative models for language generation, particularly based on transformers have shown remarkable performance in domains dealing with language.
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
Generative Models for Neural Fields Ivan Skorokhodov, Ph.D. Student, Computer Science Feb 15, 20:10 - 22:00 B1 L2 R2202 Deep generative models In computer vision, generative AI models are typically built for images, videos, and 3D objects. Recently, there has emerged a paradigm of neural fields, which unifies the representations of such types of data by parametrizing them via neural networks. In this thesis, we develop generative models for images, videos, and 3D scenes which treat the underlying data in such a form and explore the benefits which such a perspective provides.
Extracting Semantic and Geometric Information in Images and Videos using GANs Rameen Abdal, Ph.D. Student, Computer Science Feb 15, 18:00 - 20:00 B1 L2 R2202 GaN The success of Generative Adversarial Networks (GANs) has resulted in unprecedented quality both for image generation and manipulation. Recent state-of-the-art GANs (e.g., the StyleGAN series) have demonstrated outstanding results in photo-realistic image generation. In this dissertation, we explore the latent space properties, including image manipulation, extraction of 3D properties, and performing various weakly supervised and unsupervised downstream tasks using StyleGAN and its derivative architectures.
Stylistic and spatial disentanglement in GANs Yazeed Alharbi, Ph.D., Computer Science Aug 12, 14:00 - 16:00 KAUST Computer Vision machine learning generative adversarial network Deep learning This dissertation tackles the problem of entanglement in Generative Adversarial Networks (GANs). The key insight is that disentanglement in GANs can be improved by differentiating between the content, and the operations performed on that content. For example, the identity of a generated face can be thought of as the content, while the lighting conditions can be thought of as the operations.
