IEEE Xplore Search Results

Showing 1-25 of 4,715 resultsfor

Filter Results

Show

Results

This paper describes our current work in the design and development of web-based 3D reconstruction and visualization frameworks for medical data and presents a design framework for web-based 3D visualization and interaction for medical data. We implement a web-based 3D medical data visualization application with X3D technology. The web-based X3D framework integrated with a modular approach can ext...Show More
Aiming at the lack of 3D model design function of the existing 3D printing cloud service platform so that 3D modeling based on cloud was difficultly accomplished, an online 3D modeling system - 3D Rubik's Cube, was introduced in this paper. The online 3D modeling was achieved by Web front end technology such as the third-party graphics library of WebGL - Three.js, and the establishment of Web serv...Show More
Some key technologies of 3D visualization GIS, which include 3D data acquiring, 3D geometry modeling, virtual reality, 3D spatial analysis, large terrain real-time roaming, indoor roaming and 3D Web GIS, can be introduced into geosciences. In this paper, analysis and management method of spatial information in 3D GIS are used in the process of basin modelling. According to geometry and mechanical ...Show More
In the paper, we propose a 3D shape descriptor which can be applied to areas such as non-rigid 3D shape analysis and retrieval. We start with the calculation of the Wave Kernel Signature (WKS) and the scale-invariant Heat Kernel Signature (siHKS) of surface points belong to a 3D shape. Then we combine them together and obtain their principle components by PCA (principle component analysis), which ...Show More
In order to solve the problem that the existing 2D video communication has a high bandwidth occupancy rate, the inability to present three-dimensional portraits of characters and the high dependence of three-dimensional projection technology on hardware, we propose a 3D communication framework that integrates 3D reconstruction and rendering display. The framework transmits the video stream to the ...Show More
The 3D face quality assessment framework is used for quality inspection of the 3D face reconstructions models. It mainly detects the holes of the 3D face model, counts the number of holes, and returns the data results to the HTML page. This work can further improve the management of 3D reconstruction models, detect the quality of modeling, improve the utilization of the model, prepare for the subs...Show More
Recent advances of 3D acquisition devices have enabled large-scale acquisition of 3D scene data. Such data, if completely and well annotated, can serve as useful ingredients for a wide spectrum of computer vision and graphics works such as data-driven modeling and scene understanding, object detection and recognition. However, annotating a vast amount of 3D scene data remains challenging due to th...Show More
Provisioning 3D video stream-based services online in an acceptable quality, even in a wireless access environment, is a big challenge for Future Internet service providers. Only few empirical results are known about the user perceived quality of these kinds of services. In this paper we describe a statistical analysis of the relationship between Quality of Experience and service attributes for ac...Show More
“Digital holography for 3D and 4D real-world objects' capture, processing, and display” (acronym “Real 3D”) is a research project funded under the Information and Communication Technologies theme of the European Commission's Seventh Framework Programme, and brings together nine participants from academia and industry (see www.digitalholography.eu). This three-year project marks the beginning a lon...Show More
A large body of recent researches has done in the field of 3D-reconstruction, around deep neural networks. In spite of the fact that many significant advances have been made by deep neural networks in 3D reconstruction, the high architectural and computational complexity still pose a big challenge for using these methods on edge devices such as mobiles, drones and vehicles due to limitation on the...Show More
The advent of affordable virtual reality (VR) head-mounted displays (HMDs) has sparked significant research activity for creating new principles and algorithms to enable the display of VR content on these devices. However, the development of current VR content is mostly limited to experts using proprietary tools and protocols. A major goal of VR is to allow multiple people to meet and collaborate ...Show More
For 3D printed objects, research into the knowledge of design has increased in the past decade due to advances in digitization and 3D printing technologies. This has resulted in increased concerns about Intellectual Property Right issues (IPR). The problem is the inability to achieve provenance for 3D printed objects because of the lack of reference point to the original. This paper presents on-go...Show More
Recent advancements in vision-language foundation models have significantly enhanced open-vocabulary 3D scene understanding. However, the generalizability of existing methods is constrained due to their framework designs and their reliance on 3D data. We address this limitation by introducing Generalizable Open-Vocabulary Neural Semantic Fields (GOV-NeSF), a novel approach offering a generalizable...Show More
Monocular 3D human pose estimation poses significant challenges due to the inherent depth ambiguities that arise during the reprojection process from 2D to 3D. Conventional approaches that rely on estimating an over-fit projection matrix struggle to effectively address these challenges and often result in noisy outputs. Recent advancements in diffusion models have shown promise in incorporating st...Show More
Large-scale 3D structure reconstruction is a complex task. This area has attracted increasing interest in recent years in both the research community and the industry. Google, for example, used Lidar technology and a fleet of vehicles to build 3D scans of big cities such as San Francisco or New York. However, this task remains limited to a few cities and companies due to cost and access to technol...Show More
In this paper, we present on the research of semantic-based 3D model retrieval system and its developed framework. We use RDF annotation to label 3D models for improving retrieval precision. The framework contains three parts: preprocessing, feature extraction and similarity measurement. The parts are recommended to analyze the 3D model. In the preprocessing part, we deploy PCA to make models norm...Show More
The advanced 3D video system employs the multi-view video plus depth (MVD) format to support free-viewpoint navigation and comfortable 3D video. Therefore, the prediction structure of the multi-view video coding (MVC) can be used for 3D video coding. The view synthesis prediction method is designed to exploit inter-view correlation using the virtual view generation; hence it is suitable for 3D vid...Show More
Multimedia services achieved unexpected penetration over wireless networks during the last few years. Provisioning of 3D video stream-based applications and transferring 3D movies - also becoming significant within the wireless domain - is a big challenge for Internet Service Providers (ISP). Only scarce empirical results are known about the user perceived quality of such kind of services. In this...Show More
Home services are all kind of services which are provided in home environment. Legacy Researches was focused on controlling home devices and appliances. And recent works focus on the multimedia services. In the future, devices existing in the home would infer the status and intention of users and provide intelligent home services without much intervention of users. To do this, there must be contex...Show More
Robust perception is a vital component for ensuring safe autonomous driving. Automotive radar (77 to 81 GHz) offering weather-resilient sensing provides a complementary capability to the vision-or LiDAR-based autonomous driving systems. Raw radio-frequency (RF) radar tensors contain rich spatiotemporal semantics besides 3D location information. Most previous methods take in 3D (Doppler-range-azimu...Show More
In this paper, a dual circular polarized (CP) spherical conformal antenna array is designed based on a 3D printing framework. The 3D printing technology is employed to simplify the manufacturing process and reduce the cost. There are 23 elements arranged on the hemispherical surface with an optimized distribution. It also has the ability to scan a beam within the hemispherical coverage.Show More
Recent years have witnessed a growing interest in online RGB-D 3D reconstruction. On the premise of ensuring the reconstruction accuracy with noisy depth scans, making the system scalable to various environments is still challenging. In this paper, we devote our efforts to try to fill in this research gap by proposing a scalable and robust RGB-D 3D reconstruction framework, namely Chunk-Fusion. In...Show More
We present an efficient 3D object detection framework based on a single RGB image in the scenario of autonomous driving. Our efforts are put on extracting the underlying 3D information in a 2D image and determining the accurate 3D bounding box of object without point cloud or stereo data. Leveraging the off-the-shelf 2D object detector, we propose an artful approach to efficiently obtain a coarse ...Show More
Medical display systems are valuable tools in enabling the clinicians in the field of radiation therapy to view a patient's multi-modal information and treatment plan details. The effectiveness of display systems is further improved by including computer-based visualization systems that deliver the content comprehensively. In this paper, we present a medical display and visualization framework for...Show More
A visual design platform enables geographically dispersed users to cooperate with each other. This paper proposes a real-time collaborative framework for 3D design based on HTML5. By using this framework to build collaborative web applications, users can work collaboratively to assemble 3D components, expand the component library, and manage users and data. Moreover, the framework can also synchro...Show More