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 24 for “"3D Generation"”.
-
Unified 3D Understanding: 3D Generation And Registration
In modern society, advancements in 3D technologies have enabled the creation of more immersive and realistic virtual experiences while significantly enhancing real-world applications. The widespread adoption of 3D modeling, computer graphics, and virtual reality across industries—from entertainment …
-
Benchmarking Current Progress in 3D Content Generation
In recent years, 3D generation has rapidly advanced with the development of powerful generative AI models capable of producing high-quality 3D content from various modalities, including text, images, and multi-view inputs. These advancements have significantly accelerated progress in applications …
-
Synthesis by analysis : understanding and generating the 3D open world
… remarkable success in text, image, and video generation. However, comparable breakthroughs have not yet been achieved in 3D generation. This dissertation focuses on three fundamental challenges in 3D generation. The first challenge concerns 3D representation. In contrast to the 2D domain, …
-
Mining Visual Knowledge from Pre-trained Models
… tasks such as recognition, dense prediction, 3D generation, and reference-based image completion.
-
3D Shape Generation through Point Transformer Diffusion
… which have demonstrated promising results in 3D point cloud generation. Meanwhile, Transformer-based models have achieved impressive outcomes across various benchmarks in the field of 3D point cloud understanding. However, the integration of a Transformer based on the local self-attention …
-
Generative AI Framework for 3D Object Generation in Augmented Reality
… for real-time creation of three-dimensional (3D) objects in augmented reality (AR) environments. The primary goal is to convert diverse inputs, such as images and speech, into accurate 3D models, enhancing user interaction and immersion. Key components include advanced object detection …
-
Creating 3D content from a single image
… (XR), have unlocked significant potential for 3D environments. This progress has driven a growing demand for diverse 3D content that brings people's imaginations to life. However, the creation of high-quality 3D content remains a labor-intensive process, requiring substantial effort from human …
-
Laboratory and numerical studies of internal wave generation and propagation in the ocean
… the ocean, it is important to characterize their generation. The two-dimensional generation problem has been studied for four decades, with ample experimental, numerical, and theoretical results. Most of this past work has also been done using linear, inviscid approximations. However, wave …
-
Towards Robust and Generalizable Intelligence through Adversarial Examination and Generative Models
… on tasks ranging from image recognition and 3D pose estimation to visual content generation and large-scale language modeling. Yet these models remain brittle: they can fail under distribution shifts, exhibit systematic vulnerabilities to small but structured perturbations, and produce …
-
Unsupervised scene understanding
… the majority of work on image understanding and generation. Image-only models like DINO and image-text models like CLIP learn powerful representations that are adapted and used in state-of-the art segmentation, captioning, image and 3D generation, and more. Since these models have “seen” a large …
-
Deep Learning for Infinite Virtual Urban Environment Generation
… in games or Virtual Reality applications in 3D. Deep Learning technologies, which have advanced in various scientific research fields at an extremely high speed, have brought new possibilities to generate the virtual urban environment. Our research is concentrated on generating virtual urban …
-
Learning to Create 3D Content
Modeling highly realistic virtual worlds in 3D is the holy grail for visual content creation, and obtaining high quality 3D models is an indispensable part of it. 3D models are used extensively in the film and gaming industry, and we are foreseeing growing demand from novel applications such as …
-
Systematic visual fidelity: from perceptual interrogation to generative construction
… motion, or identity of the subject. For text-to-3D generation, I present YouDream, which integrates structural constraints (anatomical pose priors) to ensure geometric fidelity in generated 3D animals. For video editing, I present VidMP3, which integrates temporal functional constraints (motion …
-
Toward spatial intelligence: structured visual generation and verifiable 3D reasoning
… world modeling—from video diffusion models to 3D scene generators—learn world structure implicitly from pixels, producing plausible outputs that lack explicit structural and spatial understanding. This dissertation investigates how AI can achieve genuine spatial intelligence through three …
-
From objects to worlds: scalable learning of 3D assets
Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2027-12-01
-
Improving Consistency in Generated 3D Assets From Hand-Drawn Sketches for Rapid Game Prototyping and Development
… (AI) is becoming a popular tool for creating 3D video game content. However, frustration arises when the AI does not follow the creative directive of the designer, producing something closer to the average of the dataset rather than assisting the designer in their own creations. This thesis …
-
SIMPLIFYING 3D LEARNING: INTEGRATING PRIOR KNOWLEDGE AND DECOMPOSING COMPLEXITY
This thesis addresses fundamental challenges in 3D learning and modeling—data scarcity, ineffective prior integration, and computational complexity—through two complementary principles: strategic integration of domain-specific priors and systematic decomposition of complex problems into tractable …
Page 1 of 2