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 93 for “"3D objects"”.

  1. A generative grammar for 2D manufacturing of 3D objects

    … to engage with the superficial aspects of the objects they design and 2. The symbolic 3D environments of current design software are the ideal medium for design because they hide from the user the contingencies of physical matter. I examine these assumptions and the potential of a generative …

    mit Repository record for A generative grammar for 2D manufacturing of 3D objects (opens in a new tab)

  2. Comparison of performance for visual feedback and cursors in mid-air grasping of 3D objects

    … to help minimize the use of visual effects on objects that may draw user focus from their intended target.

    uoit Repository record for Comparison of performance for visual feedback and cursors in mid-air grasping of 3D objects (opens in a new tab)

  3. HandsOn : a portable system for collaboration on virtual 3D objects using binocular optical head-mounted display

    … often have to collaborate remotely on 3D content, especially in fields such as urban planning or architectural design. We propose HandOn, a portable system for collaboration on virtual 3D objects. HandsOn leverages the recent advances in optical head-mounted display and finger tracking …

    mit Repository record for HandsOn : a portable system for collaboration on virtual 3D objects using binocular optical head-mounted display (opens in a new tab)

  4. Generative adversarial modeling of 3D shapes

    Given a 3D shape, humans are capable of telling whether it looks natural. This shape priors, namely the perception of whether a shape looks realistic, are formed over years of our interactions with surrounding 3D objects, and go beyond simple definition of objects. In this thesis, we propose two …

    mit Repository record for Generative adversarial modeling of 3D shapes (opens in a new tab)

  5. 3D object recognition and retrieval using navigating robots with active vision : "MROLR", a mobile robotic object locator and retriever

    … (pose determining), recognizing, and retrieving 3D objects in an indoor environment. Key related contributions include the development of 3D object-model creation and editing facilities, and the application of a vision enhanced navigation algorithm.

    vu-aus Repository record for 3D object recognition and retrieval using navigating robots with active vision : "MROLR", a mobile robotic object locator and retriever (opens in a new tab)

  6. Object Modelling by Example

    … we develop a number of methods for modelling 3D objects by example. Jump maps provide fast and flexible reuse of texture imagery in object modelling. Geodesic fans extend the local statistical techniques forming the basis for traditional image-based data-driven methods to 3D surfaces, and …

    uiuc Repository record for Object Modelling by Example (opens in a new tab)

  7. Development of a novel toner for electrophotography based additive manufacturing process.

    … to conduct feasibility study of producing 3D objects by printing thermoplastic elastomer using electrophotography technique and thereafter sintering the whole layer using infrared light source .The term Selective laser printing (SLP) has been coined by the author for this new process. This …

    de-montfort Repository record for Development of a novel toner for electrophotography based additive manufacturing process. (opens in a new tab)

  8. 2d Material Inks for Printed Electronics

    … little work has been done to print on conformal 3d objects. Conformal printing is an attractive and emerging field, which can enable the deposition of specific electronic features, such as sensors and circuits, directly on to 3d objects. Functional ink deposition on 3d structures is not a trivial …

    cambridge Repository record for 2d Material Inks for Printed Electronics (opens in a new tab)

  9. 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 …

    vt Repository record for Generative AI Framework for 3D Object Generation in Augmented Reality (opens in a new tab)

  10. Interactive 3D model display in Java 3D

    <p>This thesis explores the use of Java 3D application programming interface (API) to create an interactive 3D application or applet that allows display and manipulation of complex three dimensional objects. J3dViewer, a program written using the Java 3D API, is used to illustrate the general …

    eastern-wash Repository record for Interactive 3D model display in Java 3D (opens in a new tab)

  11. Evaluating Eye-Tracking Multimodal Interactions in Virtual Reality

    … and close-up grabbing during interactions with 3D objects. A user study was conducted to compare the three interaction methods. The findings provide evidence that eye-tracking multimodal interactions outperforms both hand tracking methods across multiple metrics.

    calgary Repository record for Evaluating Eye-Tracking Multimodal Interactions in Virtual Reality (opens in a new tab)

  12. Extraction of 3D Object Representations from a Single Range Image

    … automatic construction of a computer model of 3D solid objects from a single range image. This research has many real world applications, including robotic environments and the inspection of industry parts. The most common methods for 3D-object extraction are based on stereo reconstruction and …

    vt Repository record for Extraction of 3D Object Representations from a Single Range Image (opens in a new tab)

  13. Learning Disentangled Representations of Holograms via Deep Generative Model

    … technologies of deep learning and holographic 3D displays. It demonstrates the strength of learning models and also identifies the challenges and limitations of conventional hologram computation methods for 3D scenes. These motivate us to explore the issues and seek solutions via deep …

    cambridge Repository record for Learning Disentangled Representations of Holograms via Deep Generative Model (opens in a new tab)

  14. First Principles of Line Drawings

    … for creating line drawings from photographs or 3D models. Current methods often rely on high quality paired datasets to automate the creation of line drawings. We observe that line drawings are encodings of scene information that convey 3D shape and semantic meaning. We bake these observations …

    mit Repository record for First Principles of Line Drawings (opens in a new tab)

  15. Improving Vision-Based Robotic Grasping for Enhanced Comprehensibility

    … developed on orthographic images of prismatic objects with complete object information. The insights gained from the implementation are used to extend the three-step model to perspective depth images of 3D objects with incomplete object information. This extension includes probabilistic CNNs …

    bielefeld Repository record for Improving Vision-Based Robotic Grasping for Enhanced Comprehensibility (opens in a new tab)

  16. Robust Computer Vision beyond Lₚ Adversaries

    … introduces a novel simulation-based framework, 3DB, designed for experimenting with arbitrary and semantically preserving perturbations on physically accurate 3D models directly instead of 2D images. The utility of this framework is demonstrated through its ability to diagnose and enhance the …

    mit Repository record for Robust Computer Vision beyond Lₚ Adversaries (opens in a new tab)

  17. Coordinating construction by a distributed multi-robot system

    … algorithm for the coordinated assembly of 3D objects that consist of multiple types of parts, using a networked team of robots. We describe the algorithm and analyze its stability and adaptation properties. We partition construction in two tasks, tool delivery and assembly. Each task is …

    mit Repository record for Coordinating construction by a distributed multi-robot system (opens in a new tab)

  18. How To Pack Anything

    3D printers can make anything, from household tools to rocket engines, so long as the models can be packed into a given enclosure. The denser the packing, the more efficient the print is. Unfortunately, modern packing research has struggled with complex shapes and even proprietary packing software …

    mit Repository record for How To Pack Anything (opens in a new tab)

Page 1 of 5