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 27 for “"Image Editing"”.
-
Inverse rendering techniques for physically grounded image editing
… intrinsic scene properties from single images. The goal of these inverse rendering techniques is to estimate the configurations of scene elements (geometry, materials, luminaires, camera parameters, etc) using only information visible in an image. Such algorithms have applications in …
-
Image editing and interaction tools for visual expression
… extremely common in our daily life. However, images are difficult to edit and interact with. From a user's perspective, it is important to interact freely with the images on his/her smartphone or ipad. In this thesis we develop several image editing and interaction systems with this idea in …
-
On the application of AI in subjective image editing
Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2026-05-01
-
Implementation of translation techniques, use of software and image editing in legal documents.
… the specialization course, including, translated images, a birth, marriage, and divorce certificate, a university transcript, a diploma, and a protocol of agreement. We chose the right process of translation with seven important steps: reading the text, analysis, and research, translation, taking …
-
Natural Language Driven Image Edits using a Semantic Image Manipulation Language
… one such application - natural language based image editing. We propose a novel framework to go from free-form natural language commands to performing fine-grained image edits. Recent progress in the field of deep learning has motivated solving most tasks using end-to-end deep convolutional …
-
Vector Field Manipulations in Three-Dimensional Time-Varying Flow Data Compression and Image/video Editing
We propose an image editing system that decouples feature position from pixel color generation to achieve a morph that preserves texture detail and orientation near the dragged silhouette, synthesized using the original image as an anisotropic texture. We introduce a new distortion to patch-based …
-
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 …
-
Light source relighting for indoor scene photos with deep neural networks
… a method to detect the light sources in a given image of an indoor scene, computationally adjust their lighting intensity, and re-render the edited scene as an image. By doing so, we can visually relight the image--effectively turning the light source "on" or "off" in the image. This thesis …
-
Forensic research on detecting seam carving in digital images
Digital images have been playing an important role in our daily life for the last several decades. Naturally, image editing technologies have been tremendously developed due to the increasing demands. As a result, digital images can be easily manipulated on a personal computer or even a cellphone …
-
Learning Low-Level Priors from Images for Inference and Synthesis
… 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 dimensions, it is important to …
-
Interactive and Controlled Visual Content Generation
… that explores a brushstroke decomposition of images, enabling granular control and iterative collaboration between users and generative systems. Second, we present PAIR Diffusion, a comprehensive image editing framework that integrates diverse tasks such as inpainting, object addition, and …
-
Dynamic Scene Editing via Semantically Trained 3D Guassians
Image-based 3D scene reconstruction continues to be a challenge as it involves solving both the sufficient 3D representation problem and the 3D reconstruction itself. One approach to tackle the rendering problem is 3D Gaussian Splatting because of its potential to produce fast and realistic renders …
-
Garment Design Workflows for On-Demand Machine Knitting
… knitting program generation from a single image, together with a machine learning framework that enables it. Second, I describe a parametric, primitive-based design tool that merges inspirations from both computer-aided design and pixel-based image editing. Finally, I propose a novel …
-
From brush painting to high relief.
… stroke extraction algorithm could be used for image editing. As a result, the proposed brush stroke extraction algorithm is specifically geared towards paintings with each brush stroke drawn very purposefully, such as Chinese paintings, Rosemailing paintings, etc.
-
Emergent Capabilities of Generative Models: “Software 3.0” and Beyond
… distance, metrics that are used to evaluate image synthesis quality. We then introduce a GAN framework, GANalyze, that allows one to make targeted manipulations to various cognitive attributes of GAN generated imagery, such as memorability and emotional valence, and use this framework to …
-
How Data Drives ML Models Performance
… models: backdoor attacks and malicious data editing. In this first threat model, an adversary injects a few doctered samples into the training set to control model predictions at inference time. We study the effect of these malicious samples on model behavior and then propose a framework for …
-
A robust patch-based synthesis framework for combining inconsistent images
Current methods for combining different images produce visible artifacts when the sources have very different textures and structures, come from far view points, or capture dynamic scenes with motions. In this thesis, we propose a patch-based synthesis algorithm to plausibly combine different …
-
The effect of attribute emphasis on photographic illustrations for concept attainment by learners having varying degrees of field dependence
… which had been modified using digital image editing to emphasize the critical attributes of each leaf. Following the lesson, each participant took a computer-based, 15-item multiple choice test on identification, and then a second 20-item test requiring identification of mounted leaf …
-
Image Co-saliency Detection and Co-segmentation from The Perspective of Commonalities
Image co-saliency detection and image co-segmentation aim to identify the common salient objects and extract them in a group of images. Image co-saliency detection and image co-segmentation are important for many content-based applications such as image retrieval, image editing, and content aware …
-
Evaluating interactions and decision-making by annotators and users in computer vision systems
… helpful when objects were less distinctive or image quality was poor. At the training stage, where annotators’ norms and biases shape the training data, we substituted gendered terms in existing image captioning datasets with gender-neutral equivalents to reduce gender bias and examine the …
Page 1 of 2