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 30 for “"3D understanding"”.
-
Representation learning for multi-view 3D understanding
… from multiple views is a central step towards 3D vision and spatial AI in general, with rich downstream applications such as 3D reconstruction and 3D scene understanding. In this dissertation, we study how to design the representation of multi-view images for 3D understanding. One preliminary …
-
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 …
-
Perceptual Relationship and Representation Learning for 3D Understanding and Quality Enhancement
3D modeling plays a crucial role in a wide variety of real-world applications such as autonomous driving, smart cities, entertainment, education, and video game development. Over the past decades, research has focused on enhancing 3D understanding and improving the quality of 3D representation and …
-
Annotation of 3D Object Pose from Egocentric Video
… For extended tasks such as AR and robotics, 3D understanding is needed to learn human skills. A new dataset called Indoor 3D Egocentric Object (IDEO) was created to address the shortcomings of existing datasets. Part of this dataset includes annotated 9-DOF pose of objects being manipulated …
-
Mesoscale deformation and damage characterisation of woven fibre-reinforced composites
… damage development. Therefore, an improved understanding of this behaviour is necessary for enhanced performance prediction through modelling and simulation, and hence confidence in design application under load. Advanced characterisation techniques are required to acquire this data …
-
Synthesis by analysis : understanding and generating the 3D open world
… 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, where data is structured on regular pixel grids, 3D generation requires modeling …
-
Large-scale labeled 3D CAD dataset and classification benchmark
Recent deep learning methods for 3D understanding have achieved high levels of performance in the classification task on existing datasets of simple shapes. This work sources objects from GrabCAD Library to organize a new dataset of complex shapes generally created for engineering use cases and …
-
Hierarchical and Hardware-Aware Optimization for Enhancing AI Model Efficiency: From Bits to Modules to Models
… processing, as well as Omni-Recon for efficient 3D understanding at the model level. These techniques collectively enable real-time execution of complex AI models on everyday devices, advancing the development of efficient AI solutions for ubiquitous edge intelligence.
-
Mutual exclusivity bias and spatial reasoning in Vision-Language Models
… 1) Spatial preposition comprehension through 3D information, and 2) Mutual exclusivity bias, which facilitates object-word association. We begin by examining the generalization ability of 3D reconstruction models, identifying key factors that influence their capacity to infer complete 3D …
-
Computer Vision for Light-Field Medical Imaging: FPGA Image Processing System and Depth Acquisition GAN
… from a light field array requires a precise 3D understanding of the scene being imaged. For use in a surgical environment, these images must be captured and rendered with consistently high resolution and low latency. In this paper, we present two systems to improve the latency and precision …
-
Object-Centric Scene Understanding via Lidar-Based 3D Object Detection
3D scene understanding is a fundamental challenge in designing autonomous systems that navigate in the real world. With applications in autonomous driving to warehouse robotics, effective 3D understanding has the ability to revolutionize a number of industries. Understanding complex scenes requires …
-
Label-Efficient 3D Point Cloud Understanding: From Representation Learning to Foundation Model Adaptation
Point clouds are the native output of modern 3D sensors that power autonomous driving, robotics, and augmented reality, yet their irregular, permutation-invariant, and geometrically rich structure - together with the high cost of 3D annotation - makes fully supervised learning impractical. In this …
-
Learning to optimize for geometry processing
… etc. Thanks to the popularity of portable 3D scanning devices and the emergence of big 3D data and exciting progress in artificial intelligence, there is a shift in this field from reconstructing and processing a single model to developing techniques that enable 3D models as a data modality …
-
3D spatial layout and geometric constraints for scene understanding
… vision approaches tend to ignore this aspect of understanding images. In this work, we build representations and propose strategies for exploiting such constraints towards extracting a 3D understanding of a scene from its single image. We model a scene in terms of its spatial layout abstracted as …
-
Unconstrained 3D face reconstruction from photo collections
This thesis presents a novel approach for 3D face reconstruction from unconstrained photo collections. An unconstrained photo collection is a set of face images captured under an unknown and diverse variation of poses, expressions, and illuminations. The output of the proposed algorithm is a true …
-
The development of functional hyaluronan hydrogels for neural tissue engineering
… influence the differentiation of NSPCs in 2D and 3D. HA hydrogels successfully support long term culture of neural cells in 3D, and encourage the formation and extension of neurites of several cell types including human, mouse and rat neuronal precursor and stem cells. These results demonstrate …
-
Exploring the Sinonasal Cavity in Three Dimensions: Teaching Otolaryngology Surgical Trainees Clinical Anatomy Using a Web-based Learning Resource
… therefore have a thorough three-dimensional (3D) understanding of the sinonasal space to avoid disorientation when surgically navigating through a limited endoscopic view. However, learning of this anatomical region is hampered by the complexity of anatomy as well as limitations in current …
-
Landscape response to glacial-interglacial cycles: insights from a southern North Sea offshore wind farm dataset
… that evolved during changes in past climates aid understanding the responses to future changes in climate. The bathymetry of the southern North Sea region makes it an attractive location for wind farm developments. The integration of a dense 2D grid of seismic reflection data, with …
-
Representation learning for point cloud understanding
With the rapid advancement of technology, 3D data acquisition and utilization have become increasingly prevalent across various fields, including computer vision, robotics, and geospatial analysis. 3D data, captured through methods such as 3D scanners, LiDARs, and RGB-D cameras, provides rich …
-
Hybrid representations in 3D vision
… to understand and process visual content from 3D sensors is important for enabling them to reason about the inherently 3D world we live in. Due to the high cost of 3D scanners, the availability of large-scale 3D dataset used to be scarce. Existing data-driven approaches have been mainly …
Page 1 of 2