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 20 of 38 for “"Text to Image"”.
-
Quantitative and Qualitative Analysis of Text-to-Image models
The field of image synthesis has seen significant progress recently, including great strides with generative models like Generative Adversarial Networks (GANs), Diffusion Models, and Transformers. These models have shown they can create high-quality images from a variety of text prompts. However, a …
-
Concepts from unclear textual embeddings for text-to-image synthesis
Automatically generating images based on a natural language description is a challenging problem with several key applications in the fields of retail, marketing, education and entertainment. In the last few years, some progress has been made in this direction specifically by using Generative …
-
Glass onion: Compositional text-to-image generation using diffusion models and LLMs
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-02-04 without embargo terms
-
A Submodular Approach to Find Interpretable Directions in Text-to-Image Models
Text-to-image models have significantly improved the field of image editing. However, finding attributes that the model can actually edit is still a remaining challenge. This thesis proposes a solution to this problem by leveraging a multimodal vision-language model (MMVLM) to find a list of …
-
Social stereotypes in text-to-image generation: Examining user perceptions and debiasing strategies
Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2027-05-01
-
Learning Low-Level Priors from Images for Inference and Synthesis
… critical for both downstream applications and photorealistic synthesis. Tasks such as image classification, semantic segmentation, and text-to-image generation parse the scene in terms of high-level properties of objects and scene. Along with understanding and creating visual media along these …
-
Controlled training data generation with diffusion models
In this work, we present a method to control a text-to-image generative model to produce training data specifically “useful” for supervised learning. Unlike previous works that employ an open-loop approach and pre-define prompts to generate new data using either a language model or human expertise, …
-
Leveraging the Latent Space for Model Understanding and Optimization
… performance on tasks such as classification or image generation. However, these models are typically limited by two key factors. First, models such as those used in tasks of text-to-image generation lack interpretation. Second, models that leverage the latent space to represent data struggle to …
-
Multi-Subject Image Generation
Diffusion models excel at text-to-image generation, especially in subject-driven generation for personalized images. However, existing methods are inefficient due to the subject-specific fine-tuning, which is computationally intensive and hampers efficient deployment. Moreover, existing methods …
-
Re_Imaged: Reimaging architecture through artificially intelligent generated images
… technique that exists everywhere in our day-to-day life. From a simple Google search that provides answers to any questions, to autocorrect suggestions provided while writing emails, we encounter AI in every next phase of our life. Humans have developed an invisible trust in AI that remains …
-
Constructing three-dimensional virtual spaces with the application of artificial intelligence
… It evaluates a five-stage workflow combining text-to-image generation, image-to-3D reconstruction using Tencent Hunyuan3D 2.0, and manual optimization in Blender. The workflow was applied to architectural and sculptural landmarks to test rendering performance on a Meta Quest 3 headset. Results …
-
Data-Efficient Bilingual Lexicon Induction with Pretrained Language Models
… data-efficient BLI approaches aimed at automatically inducing high-quality bilingual dictionaries in low-data scenarios, thereby bridging the lexical gaps between languages. While previous BLI methods rely on mapping static word embeddings, inspired by the paradigm shifts towards …
-
IlluSonnet: Using Generative AI to Create Illustrations for Sonnets
Poetry evokes imagery, and writers and readers alike desire to translate the artful wordplay to a beautiful image. To facilitate this process, we built IlluSonnet, a system that creates illustrations for poetry using text-to-image generative AI models. IlluSonnet works by labelling keywords, …
-
CLIP-RS: A Cross-modal Remote Sensing Image Retrieval Based on CLIP, a Northern Virginia Case Study
Satellite imagery research used to be an expensive research topic for companies and organizations due to the limited data and compute resources. As the computing power and storage capacity grows exponentially, a large amount of aerial and satellite images are generated and analyzed everyday for …
-
Uncertainty-Inclusive Contrastive Learning for Leveraging Synthetic Images
Recent advancements in text-to-image generation models have sparked a growing interest in using synthesized training data to improve few-shot learning performance. Prevailing approaches treat all generated data as uniformly important, neglecting the fact that the quality of generated images varies …
-
Specialization of Vision Representations with Personalized Synthetic Data
… works have successfully applied synthetic data to general-purpose representation learning, while advances in Text-to-Image (T2I) diffusion models have enabled the generation of personalized images from just a few real examples. Here, we explore a potential connection between these ideas, and …
-
Developing frameworks for an equitable future: from building decarbonization to generative modeling.
In this thesis I develop computational frameworks to understand equity under two perspectives: building decarbonization policy and generative modeling. Part 1 - Equitable building decarbonization Buildings significantly contribute to global carbon emissions, necessitating urgent decarbonization to …
-
Learning New Dimensions of Human Visual Similarity using Synthetic Data
… of pixels and patches. These metrics compare images in terms of their low-level colors and textures, but fail to capture mid-level similarities and differences in image layout, object poses, and semantic content. In this thesis, we develop a perceptual metric that assesses images holistically. …
-
From narrative to spectacle: An examination of contemporary theatre performance
… thesis takes its starting point the shift from text to image dominated representations of the world. It argues the parallel shifts in theatre practice and reception away from work which subordinates itself to textual narrative and towards theatre with foreground the non-textual theatrical …
-
From narrative to spectacle: An examination of contemporary theatre performance
… thesis takes its starting point the shift from text to image dominated representations of the world. It argues the parallel shifts in theatre practice and reception away from work which subordinates itself to textual narrative and towards theatre with foreground the non-textual theatrical …
Page 1 of 2