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 11 of 11 for “"3D content creation"”.
-
3D CONTENT CREATION FROM IMAGES
… However, dimensionality is reduced from 3D to 2D, when we visually capture the world with the ubiquitous cameras. The loss of this single dimensionality restricts the perspective from which a viewer could parse and explore the captured world. Hence, it is of particular interest to recover …
-
Machine Learning for 3D Content Creation
… many industries are shifting towards massive 3D virtual worlds. As the basic building blocks for 3D virtual worlds, 3D content demands high standards of realism, quality, quantity and diversity. Nonetheless, conventional approaches for 3D content creation necessitate substantial manual labor …
-
Compositional 3D Content Creation with Machine Learning and Procedural Modeling
Synthetic content creation offers a cost-effective alternative to the labor-intensive process of data collection and annotation for training large-scale machine learning models. In computer vision, 3D graphics engines can be used to generate rendered images or videos with precise ground truth for …
-
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 …
-
Geometric Regularization and Coordinate Reparameterization for Efficient ML-based 3D Synthesis and Editing
… graphics by enabling data-driven approaches to 3D synthesis and editing from text, images, and other forms of high-level supervision. Generative models, neural representations, and differentiable optimization have greatly expanded the flexibility of 3D content creation, allowing complex scenes …
-
TOWARDS PHYSICALLY-GROUNDED AND SCALABLE 3D VISUAL MODELING
… these approaches fundamentally lack explicit 3D modeling and physical reasoning, limiting their applicability in real-world scenarios that require geometric consistency and physics-aware modeling. This thesis aims to develop physically-grounded and scalable 3D visual modeling frameworks that …
-
Understanding semantics and geometry of scenes
… robotics and autonomous vehicles, as well as in 3D content creation and video editing. The focus of this research is on three specific tasks: scene graph generation, novel view synthesis, and layered scene representation. Scene graph generation involves creating a graph structure that represents …
-
Algorithms for Data-driven Geometric Stylization Acceleration
… computer algorithms for creating stylized 3D digital content and numerical tools for processing high-resolution geometric data.This thesis first addresses the problem of geometric stylization. Existing 3D content creation tools lack support for creating stylized 3D assets. They often …
-
Geometrically and Perceptually Accurate Facial Mesh Synthesis and Personalised Blendshapes Generation using Graph Neural Networks
… of geometric deep learning applications to 3D content creation has in- creased rapidly, driven by significant investments in the next generation Virtual Reality platforms and Visual Effects intensive productions. Generation of high fidelity digital humans became a focal point and one of the …
-
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 …
-
TOWARDS INVERSE RENDERING WITH GLOBAL ILLUMINATION
Obtaining 3D representations from real-world observations is a long-standing problem in computer vision/graphics with important applications in virtual/augmented reality. Inverse rendering is a technique for inferring 3D information—such as geometry, materials, and lighting—from a set of 2D images …