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 “"3D World"”.
-
Learning 3D Modeling and Simulation From and For the Real World
… of comprehending and reasoning about our 3D visual world. With just a few casual glances, we can grasp the 3D structure and appearance of our surroundings and imagine all sorts of “what-if” scenarios in our minds. Existing 3D systems, in contrast, cannot. They lack structural understanding …
-
Egomotion estimation using binocular spatiotemporal oriented energy
… correspondences or convert disparity into 3D world coordinates. There sulting algorithm has been realized in software and evaluated quantitatively on a novel laboratory dataset with ground truth as well as qualitatively on both indoor and outdoor real-world datasets. Performance is …
-
Digital twin model of two-arm collaborative robot for human arms motion simulation using reverse engineering
… files were being created to assemble it in 3D world Editor for DT formation and a grid layout was created that contained the control panel of the collaborative model digital twin to connect it with the real world. Finally, a cyber-physical system (CPS) interface was built to replicate human …
-
Starlogo camera controls and enhancements
… environment to allow students to create 3D games and simulations to help them learn programming. I improved the Sarlogo "camera", a representation of the view within a 3D world. Starlogo has a 1 person perspective camera called "Agent Eye", a 3rd person perspective camera called "Agent …
-
Gaussian Splatting Device-Architecture Co-Design for Accelerated Physical AI Inference and Reasoning
… robotics, autonomous driving, and XR/AR, demand 3D scene representations that are simultaneously photorealistic, memory-efficient, and computationally lean. Gaussian Splatting has established itself as the state-of-the-art technique for 3D scene representation, delivering photorealistic rendering …
-
Learning Consistent Visual Synthesis
… of photography, we can easily record the 3D world by taking photos and videos. In traditional images and videos, the viewer observes the scene from fixed viewpoints and cannot navigate the scene or edit the 2D observation afterward. Thus, visual content editing and synthesis become an …
-
Real-time optimal control of autonomous switched systems
… Vehicles (UAVs) that interact in a virtual 3D world.
-
Planning techniques for agent based 3D animations.
… agents capable of performing a given goal in a 3D domain continues to be a challenge for computer animated story generation systems. We present a novel prototype which consists of a 3D engine and a planner for a simple virtual world. We incorporate the 2D planner into the 3D engine to provide 3D …
-
Vision based 3D obstacle detection using a single camera for robots/UAVs
… obstacles using a single camera in an unknown 3D world for 3D motion of the robot/UAV. Obstacle detection is a pre-requisite for collision-free motion of robots/UAVs. Most of the research in this area has been for 2D motion of the ground robots and with active sensors e.g Laser range finders, …
-
Visualization and Behavioral Testing Of Common Sense Generative Programs
… powerful tools that allow for modeling complex 3D worlds containing objects and agents. Recent advances in these programs have resulted in creation of rich models whose traces represent 3D scenes, but there exist challenges in using visualizations and simulation tools for practical …
-
View Synthesis for Visuomotor Policy Learning
… often lack a comprehensive understanding of the 3D world as they are primarily trained on large-scale RGB image datasets. In this thesis, we present a new framework that equips visuomotor policies with a view synthesizer. This generative model has the ability to envision novel viewpoints and …
-
Long-range outdoor monocular localization with active features for ship air wake measurement
… extracted image points corresponding to n known 3D world points. The proposed application method operates in tandem with a tethered unmanned aerial vehicle (UAV) and mobile ground control station (GCS). The integrated localization and flight system serves as a platform for future U.S. Navy air …
-
From objects to worlds: scalable learning of 3D assets
Learning to reconstruct and generate the 3D world is a fundamental research problem in computer vision, with critical applications across diverse domains. However, the development of robust 3D generation and reconstruction systems is hindered by the scarcity of high-quality 3D data. This thesis …
-
Design and Manufacturing Methods for a Curved All-Around Camera-Based Tactile Sensor
… contact localizations, force readings, or 3D reconstructions of the sensor’s surface have a flat 2D shape; this may not be an ideal configuration for robots working in a 3D world. In this work, we present three design and manufacturing methods that were explored to build a curved, …
-
Visual analysis and synthesis with physically grounded constraints
… and not as a 2D projection of the physical 3D world. As a result, a lot of training examples are required to cover sufficiently diverse appearances and inevitably suffer from limited generalization capability. In this thesis, I propose ""inference-by-composition"" approaches to overcome …
-
Shape from Gradients. A psychophysical and computational study of the role complex illumination gradients, such as shading and mutual illumination, play in three-dimensional shape perception.
… to form a consistent and accurate percept of the 3D world is the focus of much research. In complex scenes inter-reflections of light between surfaces (mutual illumination) can occur, creating chromatic illumination gradients. These gradients provide a source of information about 3D object shape, …
-
Learning 3D Robotics Perception using Inductive Priors
… of principle-centric intelligence for the real-world. Prior knowledge (priors for short), often available in terms of past experience as well as assumptions of how the world works, helps the autonomous agent generalize better and adapt their behavior based on past experience. In this thesis, I …
-
Deep Generative Models for Unsupervised Scale-Based and Position-Based Disentanglement of Concepts from Face Images.
… it is possible to utilize clues from the real 3D world in order to guide the representation learner in the direction of disentangling facial concepts. We conduct two studies in order to test this hypothesis. First, we propose a deep autoencoder model for extracting facial concepts based on …
-
In situ genome sequencing: genomic measurement at the convergence of structure and molecular identity
… of the other: since biomolecules exist in a 3D world and function through spatially local interactions, their diverse identities and relative structural organization within a cell are two sides of one coin. Recent technologies, such as highly multiplexed fluorescent in situ hybridization and …
Page 1 of 2