检索结果-内蒙古大学图书馆

IEEE OPEN JOURNAL OF THE COMMUNICATIONS SOCIETY 2024年 5卷 4275-4292页

作者： Wu, Guanlin Lyu, Zhonghao Zhang, Juyong Xu, Jie Chinese Univ Hong Kong Sch Sci & Engn Shenzhen 518172 Guangdong Peoples R China Chinese Univ Hong Kong Shenzhen Future Network Intelligence Inst Shenzhen 518172 Guangdong Peoples R China Univ Sci & Technol China Sch Math Sci Hefei 230026 Peoples R China

The efficient representation, transmission, and reconstruction of three-dimensional (3d) contents are becoming increasingly important for sixth-generation (6G) networks that aim to merge virtual and physical worlds for offering immersive communication experiences. Neural radiance field (NeRF) and 3d Gaussian splatting (3d-GS) have recently emerged as two promising 3d representation techniques based on radiance field rendering, which are able to provide photorealistic rendering results for complex scenes. Therefore, embracing NeRF and 3d-GS in 6G networks is envisioned to be a prominent solution to support emerging 3d applications with enhanced quality of experience. This paper provides a comprehensive overview on the integration of NeRF and 3d-GS in 6G. First, we review the basics of the radiance field rendering techniques, and highlight their applications and implementation challenges over wireless networks. Next, we consider the over-the-air training of NeRF and 3d-GS models over wireless networks by presenting various learning techniques. We particularly focus on the federated learning design over a hierarchical device-edge-cloud architecture, which is suitable for exploiting distributed data and computing resources over 6G networks to train large models representing large-scale scenes. Then, we consider the over-the-air rendering of NeRF and 3d-GS models at wireless network edge. We present three practical rendering architectures, namely local, remote, and co-rendering, respectively, and provide model compression approaches to facilitate the transmission of radiance field models for rendering. We also present rendering acceleration approaches and joint computation and communication designs to enhance the rendering efficiency. In a case study, we propose a new semantic communication enabled 3d content transmission design, in which the radiance field models are exploited as the semantic knowledge base to reduce the communication overhead for distributed inference.

关键词： Three-dimensional displays Rendering (computer graphics) Neural radiance field Wireless networks 6G mobile communication Computational modeling Training 6G immersive communications 3d Gaussian splatting (3d-GS) neural radiance field (NeRF) federated learning inference

来源：评论

学校读者我要写书评

暂无评论

THE IMPACT OF GOOGLE'S APIS ON LANdSCAPE virtual REPRESENTATION 8

THE IMPACT OF GOOGLE'S APIS ON LANDSCAPE VIRTUAL REPRESENTAT...

引用

8th International conference on GeoInformation Advances (GeoAdvances)

作者： Bianconi, F. Filippucci, M. Cornacchini, F. Migliosi, A. Univ Perugia Dept Civil & Environm Engn I-06125 Perugia Italy

The field of territorial representation has undergone significant transformations in response to the proliferation of the internet, leading to the emergence of platforms dedicated to global exploration. Notably, Google Earth has assumed a pivotal role and stands as one of the most widely utilized tools for making territorial information universally accessible. Google recently introduced direct access to photorealistic 3dTiles via dedicated APIs, ushering in a new era of possibilities. This integration forms a robust foundation for crafting customized applications and interactive experiences within a geospatial three-dimensional environment. The primary objective of this research is the assessment of the accuracy and potential of the resources provided by Google within a workflow focused on digital twin processing and geospatial data visualization. To achieve this goal, a comparative analysis of distinct models was conducted, with each model representing a unique approach to three-dimensional reconstruction. The research introduces a methodology designed for easy replication in other case studies, demonstrating intrinsic scalability suitable for more complex or diverse scenarios. Furthermore, the study offers a comprehensive assessment of the differences and characteristics of the three methods analyzed, providing insights into their potential and limitations.

关键词： Representation Visualisation virtual environment Google APIs Photorealistic Tiles 3d city representation

来源：评论

学校读者我要写书评

暂无评论

High-Quality Surface-Based 3d reconstruction Using 2.5d Maps

High-Quality Surface-Based 3D Reconstruction Using 2.5D Maps

引用

IEEE conference on virtual Reality and 3d User Interfaces (IEEE VR)

作者： Song, Lingxiao Yu, Xiao di, Huijun Wang, Weiran Beijing Inst Technol Sch Comp Sci & Technol Beijing Peoples R China

ISBN: (纸本)9781665484022

Previous works on RGB-d reconstruction are based on voxels, points, or meshes,which are either too computationally expensive to represent high-resolution 3d models, or not convenient for model regularization to deal with noise and errors. In this paper, we propose a new method to reconstruct 3d models with more accurate geometric information and better texture. Our method uses abstract surfaces consisting of different points with similar information as units of the model. To reduce the complexity, we use 2.5d heightmaps to represent each surface in the reconstructed model, making it convenient to do regularization. Experiments demonstrate the effectiveness of our method.

关键词： Human-centered computing Human computer interaction virtual reality Human-centered computing visualization visualization design and evaluation methods

来源：评论

学校读者我要写书评

暂无评论

Neural radiance fields (nerf) for multi-scale 3d modeling of cultural heritage artifacts 10

Neural radiance fields (nerf) for multi-scale 3d modeling of...

引用

10th International Workshop 3d-ARCH "3d virtual reconstruction and visualization of complex architectures"

作者： Croce, V. Forleo, G. Billi, d. Bevilacqua, M.G. Piemonte, A. Caroti, G. LISPEN EA 7515 Arts et Métiers Institute of Technology Aix-en-Provence13100 France Dept. of Energy Systems Territory and Construction Engineering University of Pisa Pisa56122 Italy Dept. of Civil and Industrial Engineering University of Pisa Pisa56122 Italy

This research aims to assess the adaptability of Neural Radiance Fields (NeRF) for the digital documentation of cultural heritage objects of varying size and complexity. We discuss the influence of object size, desired scale of representation, and level of detail on the choice to use NeRF for cultural heritage documentation, providing insights for practitioners in the field. Case studies range from historic pavements to architectural elements or buildings, representing diverse and multi-scale scenarios encountered in heritage documentation procedures. The findings suggest that NeRFs perform well in scenarios with homogeneous textures, variable lighting conditions, reflective surfaces, and fine details. However, they exhibit higher noise and lower texture quality compared to other consolidated image-based techniques as photogrammetry, especially in case of small-scale artifacts. © 2024 International Society for Photogrammetry and Remote Sensing. All rights reserved.

关键词： 3d modeling

来源：评论

学校读者我要写书评

暂无评论

Applications of virtual Reality for Teaching dance History 15

Applications of Virtual Reality for Teaching Dance History

引用

15th IEEE International conference on Cognitive Infocommunications, CogInfoCom 2024

作者： Bólya, Anna Mária Gilányi, Attila Chmielewska, Katarzyna Res. Inst. of Art Theory and Methodology Hungarian Academy of Arts Budakeszi út 38 Budapest1121 Hungary Faculty of Informatics University of Debrecen Egyetem tér 1 Debrecen4032 Hungary Institute of Mathematics Kazimierz Wielki University ul. Chodkiewicza 30 Bydgoszcz85-064 Poland

ISBN: (纸本)9798350378245

virtual reality has increasingly wider applications in dance education and the presentation of dance and theater history. In this paper, we overview the results of some recent investigations related to this area. We overview the virtual reconstruction of a symbolic place of Hungarian theater, ballet and opera, the first building of the National Theater of Hungary. We shortly describe two different forms of its visualization, and we present some applications of its models in teaching dance and theater history. We also summarize some testing results related to these applications. © 2024 IEEE.

关键词： 3d reconstruction

来源：评论

学校读者我要写书评

暂无评论

Personalized Avatars Creation Based On Realistic 3d Face reconstruction 17

Personalized Avatars Creation Based On Realistic 3d Face Rec...

引用

17th International conference on Interfaces and Human Computer Interaction 2023, IHCI 2023, the 17th International conference on Computer Graphics, visualization, Computer Vision and Image Processing 2023, CGVCVIP 2023 and 16th International conference on Game and Entertainment Technologies 2023, GET 2023

作者： ding, Yueming Mok, Pik Yin School of Fashion and Textiles Hong Kong Polytechnic University Hong Kong

ISBN: (纸本)9789898704498

Personalized 3d human avatars hold great potential in the digital era, and this also enables interesting fashion applications such as virtual try-on, virtual fashion shows, and immersive online shopping experiences. Nevertheless, personalized avatars are seldom used in the fashion industry due to the requirements of specialized equipment and the tedious and computationally demanding nature of traditional personalized face modeling processes. In this paper, a novel method is presented for creating personalized fashion avatars by reconstructing a realistic 3d face from a single image. The proposed method involves transferring customized 3d facial shape and appearance, reconstructed from a single face image, onto full-body avatars with varying topologies suitable for different fashion applications. Through a comprehensive comparison with state-of-the-art face reconstruction methods, the proposed method has demonstrated high realism and richer facial details. This technology has already been applied in an augmented reality (AR) mobile application, enabling users to engage in virtual try-on experience of fashion. © 2023 Proceedings of the International conferences on Interfaces and Human Computer Interaction 2023, IHCI 2023;Computer Graphics, visualization, Computer Vision and Image Processing 2023, CGVCVIP 2023;and Game and Entertainment Technologies 2023, GET 2023. All rights reserved.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Application of 3d Gaussian Splatting target reconstruction in short-range detection 4

Application of 3D Gaussian Splatting target Reconstruction i...

引用

4th International conference on defence Technology, ICdT 2024

作者： Lou, Wenzhong Li, Chenglong Feng, Hengzhen ding, Nanxi Zhang, Zihao Ma, Wenlong Wang, Lin Science and Technology on Electromechanical Dynamic Control Laboratory School of Mechatronical Engineering Beijing Institute of Technology Beijing China

The research presented in this paper successfully introduces the emerging 3d reconstruction technology to specific application scenarios, especially for the strict requirements of information authenticity and timeliness for reconnaissance equipment and platforms. Traditional methods have the problems of slow speed and damaged reconstruction quality in processing reconnaissance information. In order to solve the problem of limited computing power of aerial detection platform and improve the reconstruction quality and efficiency of complex scenes, this paper introduces three-dimensional Gaussian Splatting (3dGS) method for testing. Experimental results show that 3dGS has excellent performance in rendering accuracy and real-time performance, which can effectively meet the performance requirements of aerial detection platforms. We tested it on a virtual dataset, and the experimental results show that it can also maintain excellent performance in the real world. © 2024 Institute of Physics Publishing. All rights reserved.

关键词： 3d modeling

来源：评论

学校读者我要写书评

暂无评论

Reimagining Lost Scenes: Street View Scene reconstruction via Multi-View Hand-drawn-Sketches 44

Reimagining Lost Scenes: Street View Scene Reconstruction vi...

引用

44th Annual conference of the Association for Computer Aided design in Architecture: designing Change, ACAdIA 2024

作者： Cao, Biru Massachusetts Institute of Technology School of Architecture and Planning United States

ISBN: (纸本)9798989176472

With many historical sites lost and only limited sketches remaining, reimagining and experiencing the 3d space of these vanished scenes is valuable. This project explores the 3d reconstruction of historical street views from multi-view hand-drawn sketches, using the recreation of Field Lane, a location described in Charles dickens’s Oliver Twist, as a case study. Although Field Lane no longer exists, its depiction offers a unique case for applying deep learning techniques to recreate lost historical settings. The study progresses from single-image reconstructions to more complex multi-view scenarios, focusing on sketches of architectural street scenes. This project is valuable for those interested in experiencing the spatial dimensions of historical settings in a 3d context. Furthermore, it holds significant potential for digital heritage and virtual reality, allowing the revival of historical sites from limited visual resources. © 2024 Association for Computer Aided design in Architecture. All rights reserved.

关键词： virtual reality

来源：评论

学校读者我要写书评

暂无评论

dense reconstruction of substation room with LSd SLAM 3

Dense reconstruction of substation room with LSD SLAM

引用

3rd International conference on Artificial Intelligence, virtual Reality, and visualization, AIVRV 2023

作者： Li, Zhaoqing Zhao, Xiaoxuan Li, Yihui College of Intelligence Science and Technology National University of Defense Technology Changsha China Faculty of Electrical and Control Engineering Liaoning Technical University Hu Ludao China

ISBN: (纸本)9781510671485

With the development of digital transmission and transformation systems, digital substations have become a prevalent trend in the electric power industry. However, the presence of many electrical components in substation environments with varying textures poses challenges for the reconstruction of a digital three-dimensional model and robot operation. To deal with that problem, this paper introduces the rich line features present in substation environments into the front-end feature tracking of 3d reconstruction in order to improve the accuracy of the 3d reconstruction. The optimized LSd algorithm is utilized for extracting line features in weak texture scenes. Additionally, a line segment merging algorithm is proposed to reduce the rate of mismatched line features and avoid redundancy through the combination of similar or repeated line segments. Finally, the paper presents a novel line feature matching method based on geometric constraints during the stage of online feature matching, which has the ability to improve matching accuracy while decreasing matching time. The experimental results demonstrate that the front-end visual odometer's optimization method proposed in this paper can offer better feature extraction and matching initial values compared to traditional methods for nonlinear optimization of the back-end of 3d reconstruction and loopback detection. © 2023 SPIE.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Fast and smart 3d modelling: An algorithmic tool based on church typology 10

Fast and smart 3d modelling: An algorithmic tool based on ch...

引用

10th International Workshop 3d-ARCH "3d virtual reconstruction and visualization of complex architectures"

作者： Scandurra, Simona Capone, Mara Palomba, daniela University Federico II of Naples Italy

Increasingly advanced technological development and the broad possibilities introduced by computer graphics and parametricsemantic modelling force us to reflect on the concept of smart models, especially in relation to the purposes for which the models themselves are created, directing research towards in-depth studies linked to the type of information that the model is intended to convey. This research shows the results obtained in the development and experimentation of a generative modelling algorithm dedicated to the rapid and semi-Automatic modelling of churches. The work stems from the need to elaborate a useful tool to prepare, in a short time, an intelligent database-graphic and informative-rapidly visualisable, dedicated to the management of churches in post-earthquake emergency conditions. The main objective is to make efficient the processes of data management and visualisation based on the seismic damage assessment sheets [d.P.C.M. 23 February 2006 (G.U. 7.3.2006, no. 55)] through procedures capable of expanding the information patrimony and, at the same time, optimising documentation and intervention times, costs and resource management (Chevrier, et al., 2009). The procedure for realising the parametric model is based on the concept of shape grammar. It allows different types of churches to be generated from the modification of basic shapes prepared according to the concept of a macro-element. It makes it possible to generate different types of churches from the modification of basic shapes prepared according to the macro-element concept (Lanzara, et al., 2021). The algorithm was tested by applying it to several case studies to evaluate its effectiveness and future implementations. © Author(s) 2024.

关键词： Religious buildings

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：