2026-09-21T02:28:43Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/125619 2025-02-06 col_2142_5131 col_2142_8888 com_2142_5130 com_2142_8887 com_2142_234

application/pdf en text Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-02-04 without embargo terms The student, Viraj Shah, accepted the attached license on 2024-07-11 at 16:42. The student, Viraj Shah, submitted this Dissertation for approval on 2024-07-11 at 16:59. This Dissertation was approved for publication on 2024-07-12 at 15:31. DSpace SAF Submission Ingestion Package generated from Vireo submission #21076 on 2025-02-04 at 21:05:03 Adaptation of Generative Models for Image Manipulation and Recontextualization Shah, Viraj 2024-07-12 Lazebnik, Svetlana Lazebnik, Svetlana Forsyth, David Schwing, Alexander Hasegawa-Johnson, Mark Generative Models Generative Adversarial Networks Diffusion Models Image Editing Image Stylization Intrinsic Image Decomposition Recontextualization eng In recent works, generative models such as generative adversarial networks (GANs) and diffusion models have demonstrated a remarkable ability to mimic the image data distributions and to synthesize highly photo-realistic images representing diverse sets of concepts. Such models capture rich semantic information of the image data, and can potentially be used as a prior in solving image manipulation and recontextualization problems. In this work, we aim to study various challenges in employing generative models as priors in solving image attribute editing, intrinsic image decomposition, and one-shot image stylization. First, we discuss the challenge of inverting a pre-trained GAN, a crucial step in exploiting the rich GAN image priors, and how we can achieve a near-perfect GAN Inversion for accurate image reconstruction and attribute editing. We extend the framework of GAN Inversion to multiple GANs that allow for jointly leveraging multiple GAN priors for the successful decomposition of an image into its intrinsic components such as albedo, shading, and specular. Further, we propose a GAN-based one-shot stylization method that can stylize an input image into multiple styles at once while using only one example of each reference style. Since the GAN-based stylization approaches are typically limited to specific subject domains, we also propose a diffusion model-based one-shot stylization approach, ZipLoRA, that allows for generating any subject in any style along with text-driven recontextualization capabilities. 2024-08 Thesis https://hdl.handle.net/2142/125619 Copyright 2024 Viraj Shah Electrical & Computer Eng Electrical & Computer Engr University of Illinois at Urbana-Champaign Ph.D. Dissertation