Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 13 of 13 for “"video generation"”.
-
Towards controllable image and video generation
Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2025-08-01
-
Concept Vectors for Zero-Shot Video Generation
Zero-shot video generation involves generating videos of concepts (action classes) that are not seen in the training phase. Even though the research community has explored conditional video generation for long high-resolution videos, zero-shot video remains a fairly unexplored and challenging task. …
-
Natural video synthesis with Generative Adversarial Networks
… state of the art neural network models for image generation, but the use of GANs for video generation is still largely unexplored. This thesis introduces new GAN based video generation methods by proposing the technique of model inflation and the segmentation-to-video task. The model inflation …
-
Efficient Generative Models for Visual Synthesis
… efficiency of generative models for image and video synthesis. First, we propose distribution matching distillation, a method that enables the training of one- or few-step visual generators by distilling knowledge from computationally expensive yet highly capable diffusion models. Next, we …
-
Training large-scale video generative adversarial networks for high quality video synthesis
Video synthesis using deep learning methods is an important yet challenging task for the computer vision community. Generative Adversarial Networks have been proved effective for generating high fidelity photo-realistic images. Recently, many video synthesis models achieve high fidelity and …
-
Towards Intelligent Videogame Generation
… emerged as revolutionary tools for image and video generation, reshaping content creation landscapes and transforming professional workflows. These techniques have significantly impacted the media creation industry, facilitating more accessible and efficient media pipelines. Nevertheless, …
-
A GAN-BASED HUMAN UV COORDINATES ESTIMATION
In image or video generation tasks that involve people, it is crucial to obtain accurate representations of the 3D human shape and appearance for efficient generation of modified content. Human UV coordinates estimation establishes correspondences between 3D human body surface representations and …
-
An efficient neural representation for videos
With the increasing popularity of videos, it has become crucial to find efficient and compact ways to represent them for easier storage, transmission, and downstream video tasks. Our dissertation proposes an innovative neural representation for videos called NeRV, which stores each video implicitly …
-
Video as the Language of Embodied Intelligence
… and training regimes accordingly. We investigate video as the foundational language, integrated with model-based planning for decision-making. This new paradigm is instantiated through two core contributions. The first is Diffusion Forcing, a hybrid modeling framework that combines causal …
-
Improve the efficiency of conditional generative models
… unlocked the potential for flexible image and video generation/editing based on text descriptions or “prompts.” Additionally, generative AI has enhanced model efficiency by supplementing datasets with synthesized data in scenarios where annotations are unavailable or imprecise. Despite these …
-
Steering Vision at Scale: From the Model Weights to Training Data
… in typographic attack resistance, improved image generation, and robust out-of-domain OCR detection. Building on this foundation, we explore methods to enhance the controllability of diffusion models. First, we tackle the challenge of unwanted concept generation. We introduce a technique to remove …
-
From objects to worlds: scalable learning of 3D assets
… domains. However, the development of robust 3D generation and reconstruction systems is hindered by the scarcity of high-quality 3D data. This thesis aims to address this scaling challenge along several dimensions. First, we introduce ShapeClipper, which leverages semantic consistency from …
-
Finding perceptually optimal operating points of a real time interactive video-conferencing system
… aims to address issues faced by real time video-conferencing systems in locating a perceptually optimal operating point under various network and conversational conditions. In order to determine the perceptually optimal operating point of a video-conferencing system, we must first be able …