检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

1,498 篇 会议
42 篇 期刊文献
3 篇 学位论文
1 册 图书

馆藏范围

1,544 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,150 篇 工学
- 753 篇 计算机科学与技术...
- 416 篇 软件工程
- 318 篇 测绘科学与技术
- 203 篇 建筑学
- 168 篇 光学工程
- 120 篇 土木工程
- 106 篇 电气工程
- 65 篇 信息与通信工程
- 65 篇 控制科学与工程
- 65 篇 生物医学工程（可授...
- 53 篇 机械工程
- 41 篇 生物工程
- 36 篇 材料科学与工程（可...
- 27 篇 仪器科学与技术
- 26 篇 化学工程与技术
- 23 篇 电子科学与技术（可...
492 篇 理学
- 222 篇 地理学
- 133 篇 物理学
- 94 篇 数学
- 48 篇 生物学
- 26 篇 化学
- 17 篇 地质学
427 篇 医学
- 398 篇 临床医学
- 33 篇 基础医学(可授医学...
- 28 篇 特种医学
- 18 篇 药学(可授医学、理...
100 篇 管理学
- 54 篇 管理科学与工程(可...
- 44 篇 图书情报与档案管...
56 篇 历史学
- 55 篇 考古学
19 篇 法学
- 19 篇 社会学
12 篇 教育学
11 篇 农学
5 篇 经济学
2 篇 文学
2 篇 军事学
1 篇 艺术学

主题

200 篇 virtual reality
154 篇 visualization
154 篇 image reconstruc...
133 篇 three-dimensiona...
109 篇 3d reconstructio...
90 篇 solid modeling
88 篇 cultural heritag...
87 篇 photogrammetry
62 篇 cameras
58 篇 augmented realit...
58 篇 surface reconstr...
51 篇 3d modelling
50 篇 3d modeling
47 篇 shape
44 篇 laser scanning
37 篇 data visualizati...
35 篇 geometry
34 篇 image segmentati...
34 篇 layout
33 篇 reconstruction

机构

14 篇 beihang univ sta...
14 篇 state key labora...
8 篇 univ debrecen fa...
6 篇 bruno kessler fd...
6 篇 beihang univ qin...
5 篇 trento
5 篇 kazimierz wielki...
5 篇 university of to...
4 篇 univ toronto on
4 篇 hajdusagi museum...
4 篇 beijing normal u...
4 篇 univ salamanca h...
4 篇 politecn milan d...
4 篇 tianjin univ tec...
4 篇 beihang universi...
4 篇 bruno kessler fd...
4 篇 univ palermo dep...
4 篇 univ ferrara dep...
3 篇 shanghai jiao to...
3 篇 shanghai ai lab

作者

22 篇 remondino f.
15 篇 barazzetti l.
14 篇 georgopoulos a.
10 篇 fassi f.
10 篇 qi yue
9 篇 previtali m.
8 篇 gilanyi attila
8 篇 yue qi
8 篇 scaioni m.
8 篇 roncoroni f.
7 篇 menna f.
7 篇 grussenmeyer p.
7 篇 luo xun
7 篇 adami a.
6 篇 tucci g.
6 篇 chmielewska kata...
6 篇 remondino fabio
5 篇 zhu yunrui
5 篇 agrafiotis p.
5 篇 achille c.

语言

1,521 篇 英文
17 篇 其他
4 篇 中文
3 篇 西班牙文

检索条件"任意字段=Conference on 3D Virtual Reconstruction and Visualization of Complex Architectures"

共 1544 条记录，以下是221-230 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

dense Real-Time Capture of Large Indoor Environments for Immersive visualization and Telepresence

Dense Real-Time Capture of Large Indoor Environments for Imm...

引用

virtual Reality and 3d User Interfaces Abstracts and Workshops (VRW), IEEE conference on

作者： Jonas Prohaska Iana Podkosova Christian Schoenauer Hannes Kaufmann TU Wien

ISBN: (数字)9798331514846

ISBN: (纸本)9798331525637

detailed reconstructions of large indoor environments are needed for many application domains, such as telepresence and as-planned-as-built comparisons for the construction industry. Usually, to obtain the desired accuracy of the reconstruction, a high-end stationary sensor and many hours of post-processing work are needed. Our methodology circumvents this obstacle by creating detailed captures of large indoor environments, including color, in real-time. To accomplish this, we created a dual-sensor setup with a mobile LidAR and an RGB-d sensor (Azure Kinect), and a dual-layer capture workflow in which a sparse point cloud capture serves as a basis for the second, dense point cloud reconstruction. In the evaluation in which we compared our resulting point cloud captures to the ground truth point cloud created by a high-end stationary LidAR, our methodology achieved the accuracy below 3 cm.

关键词： Point cloud compression visualization Telepresence Laser radar Accuracy Three-dimensional displays virtual reality User interfaces Real-time systems Indoor environment

来源：评论

学校读者我要写书评

暂无评论

MonoVAN: Visual Attention for Self-Supervised Monocular depth Estimation 22

MonoVAN: Visual Attention for Self-Supervised Monocular Dept...

引用

22nd IEEE International Symposium on Mixed and Augmented Reality (ISMAR)

作者： Indyk, Ilia Makarov, Ilya HSE Univ Moscow Russia Artificial Intelligence Res Inst AIRI AI Ctr NUST MISiS Moscow Russia

ISBN: (纸本)9798350328387

depth estimation is crucial in various computer vision applications, including autonomous driving, robotics, and virtual and augmented reality. An accurate scene depth map is beneficial for localization, spatial registration, and tracking. It converts 2d images into precise 3d coordinates for accurate positioning, seamlessly aligns virtual and real objects in applications like AR, and enhances object tracking by distinguishing distances. The self-supervised monocular approach is particularly promising as it eliminates the need for complex and expensive data acquisition setups relying solely on a standard RGB camera. Recently, transformer-based architectures have become popular to solve this problem, but at high quality, they suffer from high computational cost and poor perception of small details as they focus more on global information. In this paper, we propose a novel fully convolutional network for monocular depth estimation, called MonoVAN, which incorporates the visual attention mechanism and applies super-resolution techniques in decoder to better capture fine-grained details in depth maps. To the best of our knowledge, this work pioneers the use of a convolutional visual attention in the context of depth estimation. Our experiments on outdoor KITTI benchmark and the indoor NYUv2 dataset show that our approach outperforms the most advanced self-supervised methods, including such state-of-the-art models as transformer-based VTdepth from ISMAR'22 and hybrid convolutional-transformer MonoFormer from AAAI'23, while having a comparable or even fewer number of parameters in our model than competitors. We also validate the impact of each proposed improvement in isolation, providing evidence of its significant contribution. Code and weights are available at https://***/IlyaInd/MonoVAN.

关键词： Human-centered computing-Human computer interaction (HCI)-Interaction paradigms-Mixed / augmented reality Artificial intelligence-Computer vision-Localization, spatial registration and tracking-3d reconstruction

来源：评论

学校读者我要写书评

暂无评论

MICROPHONE ALIGNEd CONTINUOUS WEARABLE dEVICE-RELATEd TRANSFER FUNCTION: EFFICIENT MOdELING ANd MEASUREMENTS 49

MICROPHONE ALIGNED CONTINUOUS WEARABLE DEVICE-RELATED TRANSF...

引用

49th IEEE International conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Manamperi, Wageesha N. Abhayapala, Thushara d. Holmberg, Paul Australian Natl Univ Audio & Acoust Signal Proc Grp Canberra ACT Australia Dolby Labs Audio Capture Team Sydney NSW Australia

ISBN: (纸本)9798350374520;9798350374513

With the recent emergence of virtual reality, augmented reality, and mixed-reality technologies, considerable attention has been received to integrate spatial audio recording capabilities into these devices. Extracting higher order spherical harmonics from the recordings is not always possible due to complex scattering effects from the arbitrary-shaped devices, which motivates the need for modeling the acoustic properties beyond free-field convention. In this paper, we propose modeling the wearable device-related transfer function (WdRTF) that incorporates scattering, and diffraction from the device and wearer's body to an incident soundfield. We adopt the spherical wave model to translate the measurements into microphone alignment, by exploiting both magnitude and phase corrections. We use a discrete set of measurements by multiple circular arrays for efficiently estimating the WdRTF coefficients. We illustrate the WdRTF modeling procedure from a head-worn microphone array and obtain accurate reconstruction performance over frequency and 3d directions.

来源：评论

学校读者我要写书评

暂无评论

Inkjet coating combined for nanoimprinting for complex 3d patterns with nonlinear height and low residual layer 6

Inkjet coating combined for nanoimprinting for complex 3D pa...

引用

6th conference on Optical architectures for displays and Sensing in Augmented, virtual, and Mixed Reality-AR, VR, MR

作者： Schuster, Patrick Rimboeck, Johanna Vsetecka, Lisa Achleitner, Thomas Connolly, Brid Frangen, Andreas Sczyrba, Martin EV Grp 4782 St Florian Am Inn Austria Tekscend Photomasks Germany GmbH D-01109 Dresden Germany Advanced Mask Technol Ctr GmbH Co KG D-01109 Dresden Germany

ISBN: (纸本)9781510686069;9781510686076

Waveguides based on surface relief gratings are widely used to manufacture augmented reality devices such as smart glasses. They have evolved to deliver bright colors and an expansive field of view to enhance the user experience. To enable an outstanding picture quality, the light - projected from the light engine into the waveguide and diffracted in direction of the viewer - is required to be coupled out uniform from the waveguide into the viewer's eyes. diffracted light, which exits the waveguide, is lost and the picture appears less intense on the near-eye display the further it has to travel within the waveguide. Therefore, the optical design of the outcoupling surface relief gratings must ensure that the amount of light exiting the waveguide at the initial section of the outcoupling grating is minimized, while progressively increasing with further travel distance within the waveguide. This study highlights recent advancements in inkjet coating, particularly for achieving nonlinear variations in grating heights. Samples coated via inkjet will undergo nanoimprinting to create complex AR gratings with heights ranging from 50 nm to 200 nm, utilizing nonlinear height functions. In addition to addressing thickness variations, the research also covers the reliable and repeatable coating of films thinner than 30 nm. TEKSCENd Photomasks supplied the hard master, while EVG concentrated on inkjet coating of imprint polymers and subsequent NIL structuring.

关键词： Nanoimprint Lithography SmartNIL (R) Waveguides Inkjet Coating Augmented Reality

来源：评论

学校读者我要写书评

暂无评论

3d reconstruction based on monocular image sequences 6

3D reconstruction based on monocular image sequences

引用

6th International conference on Electronic Information Technology and Computer Engineering, EITCE 2022

作者： dai, Shuo Nai, Changxin Wang, Peiyun School of Information and Electronic Engineering Shandong Technology and Business University YanTai China Technology Co. Tian Jin China

ISBN: (纸本)9781450397148

Aiming at the complex operation of active 3d reconstruction technology, which is easily affected by external environment and equipment, this paper adopts a series of monocular image sequences taken by cell phone cameras from different angles to realize 3d scene reconstruction. Firstly, Structure-From-Motion (SFM) algorithm is used for sparse point cloud reconstruction, and the similarities and differences between incremental and global SFM algorithms for sparse reconstruction are compared;secondly, Multi-View-Stereo (MVS) is used for dense point cloud reconstruction, and finally, the surface and texture information of the object is recovered. The surface and texture information of the objects are recovered to achieve the reconstruction of 3d scenes. The experimental results show that the method can achieve better 3d reconstruction of monocular image sequences. © 2022 Association for Computing Machinery.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Analyse the Shape and Texture of 3d Generative Faces

Analyse the Shape and Texture of 3D Generative Faces

引用

Advances in Computing, Communication and Networking (ICAC2N), International conference on

作者： Kriti Gupta Meenu Gupta Rakesh Kumar Ahmed J. Obaid Department of CSE Chandigarh University Mohali India Faculty of Computer Science and Mathematics University of Kufa Najaf Iraq College of Techincal Engineering National University of Science and Technology Dhi Qar Iraq

ISBN: (数字)9798350356816

ISBN: (纸本)9798350356823

Research on 3d face modeling has been ongoing in the fields of Computer Vision (CV) and Computer Graphics (CG), supporting applications ranging from the creation of synthetic data to the transfer of facial expressions in virtual avatars. This work introduces a framework for 3d face generation that separates identity from expression elements to give fine control over facial expressions. The model generates high-fidelity 3d faces with remarkable appearance and shape by combining the Wasserstein Generative Adversarial Network (WGAN) and Supervised Auto-Encoder (SAE) architectures. In particular, texture synthesis is performed using the Progressive Growing of GANs (ProGAN) technique, and shape formation is made possible by the SAE architecture, which allows for the capture of complex facial traits. The model may provide reconstructions with more realism while maintaining fine-grained features and overall structure because to the fusion of WGAN and VAE. The suggested method is evaluated using both quantitative and qualitative methods. Metric standard deviation are used for the quantitative analysis, while visual examination of the rebuilt faces is used for the qualitative analysis. The outcomes of the experiments show that the suggested approach performs better in creating realistically shaped and texture 3d face reconstructions.

关键词： Solid modeling visualization Three-dimensional displays Shape Statistical analysis Computational modeling Computer architecture Faces Image reconstruction Synthetic data

来源：评论

学校读者我要写书评

暂无评论

Multi-view Based 3d Point Cloud Completion Algorithm for Vehicles 26

Multi-view Based 3D Point Cloud Completion Algorithm for Veh...

引用

26th International conference on Pattern Recognition / 8th International Workshop on Image Mining - Theory and Applications (IMTA)

作者： Ibrahim, Yahya Nagy, Balazs Benedek, Csaba Peter Pazmany Catholic Univ Fac Informat Technol & Bion Budapest Hungary Inst Comp Sci & Control SZTAKI Budapest Hungary

ISBN: (数字)9781665490627

ISBN: (纸本)9781665490627

3d vehicle shape completion is a key task in urban environment reconstruction, since the available sensors and 3d scanning procedures (such as Mobile Laser Scanning) in an outdoor city scene cannot usually extract the entire car shapes, which can be necessary for specifying their geometric properties for further analysis or realistic visualization. In this paper, we propose a novel multi-view based 3d object point cloud completion technique. In contrast to existing approaches, our method operates on 2d images formed by projecting the point cloud from several virtual camera positions around the object of interest. Both color and geometrical information is considered during the process, generating dense textured point clouds, displaying realistic patterns in the missing regions from the partial inputs. We present both quantitative and qualitative tests on various synthetic and real laser scanned vehicle point clouds, which demonstrate that our method surpasses existing state-of-the-art approaches. By applying it to vehicles from the Shapenet dataset, our approach outperforms recent techniques in terms of Earth Mover's distance (EMd) and Chamfer distance (Cd) by 43.8% and 12.17%, respectively.

关键词： Point cloud compression visualization Three-dimensional displays Shape Urban areas Lasers Sensors

来源：评论

学校读者我要写书评

暂无评论

Knowledge-distillation-based Lightweight virtual Try-On Network 2

Knowledge-Distillation-based Lightweight Virtual Try-On Netw...

引用

2nd International conference on Image Processing, Computer Vision and Machine Learning, ICICML 2023

作者： Xu, Lei Gao, Zhan Zhu, Heng Nantong University Information Science and Technology School Nantong China

ISBN: (纸本)9798350331417

As a popular research direction in deep learning in recent years, virtual try-on technology has gained more acceptance through 2d image-based methods due to their lower cost and time requirements compared to their 3d virtual try-on counterparts. However, existing image-based virtual try-on methods primarily focus on enhancing the quality of the output, resulting in complex network architectures with numerous parameters. This requires high computational power and storage costs, which hinders their development in real-time application domains. This paper presents a lightweight virtual try-on method that integrates inverted residual and knowledge distillation techniques. The architecture comprises a teacher network and a student network. The teacher network plays a crucial role in providing guidance and employs knowledge distillation to instruct the student network. The student network, which does not rely on human body representation, utilizes a style-based generative adversarial network to achieve clothing deformation. In the student network, inverted residual blocks are integrated to generate realistic try-on images. The experimental results demonstrate that our proposed method achieves a low computational cost and short runtime, while still maintaining high-quality try-on results. © 2023 IEEE.

关键词： inverted residual block knowledge-distillation style-based generative adversarial network

来源：评论

学校读者我要写书评

暂无评论

High-Quality 3d Face reconstruction with Affine Convolutional Networks 22

High-Quality 3D Face Reconstruction with Affine Convolutiona...

引用

30th ACM International conference on Multimedia (MM)

作者： Lin, Zhigian Lin, Jiangke Li, Lincheng Yuan, Yi Zou, Zhengxia Zhejiang Univ Hangzhou Peoples R China NetEase Fuxi AI Lab Guangzhou Peoples R China Beihang Univ Beijing Peoples R China

ISBN: (纸本)9781450392037

Recent works based on convolutional encoder-decoder architecture and 3dMM parameterization have shown great potential for canonical view reconstruction from a single input image. Conventional CNN architectures benefit from exploiting the spatial correspondence between the input and output pixels. However, in 3d face reconstruction, the spatial misalignment between the input image (e.g. face) and the canonical/UV output makes the feature encoding-decoding process quite challenging. In this paper, to tackle this problem, we propose a new network architecture, namely the Affine Convolution Networks, which enables CNN based approaches to handle spatially non-corresponding input and output images and maintain high-fidelity quality output at the same time. In our method, an affine transformation matrix is learned from the affine convolution layer for each spatial location of the feature maps. In addition, we represent 3d human heads in UV space with multiple components, including diffuse maps for texture representation, position maps for geometry representation, and light maps for recovering more complex lighting conditions in the real world. All the components can be trained without any manual annotations. Our method is parametric-free and can generate high-quality UV maps at resolution of 512 x 512 pixels, while previous approaches normally generate 256 x 256 pixels or smaller. Our code will be released once the paper got accepted.

关键词： high-quality 3d face reconstruction affine convolution layer representing in UV space differentiable rendering

来源：评论

学校读者我要写书评

暂无评论

A Survey of Text-guided 3d Face reconstruction

A Survey of Text-guided 3D Face Reconstruction

引用

Image Processing and Media Computing (ICIPMC), International conference on

作者： Mengyue Cen Haoran Shen Wangyan Zhao dingcheng Pan Xiaoyi Feng Northwestern Polytechnical University Xi’an China

ISBN: (数字)9798350386660

ISBN: (纸本)9798350386677

Text-guided 3d face reconstruction is an emerging field that leverages artificial intelligence to generate detailed and animatable 3d facial models from textual descriptions. This technology holds promise for revolutionizing digital content creation, avatar design, and virtual interaction by allowing users to convert textual imaginations into realistic 3d representations. This survey paper provides a comprehensive overview of the state-of-the-art methods in text-guided 3d face reconstruction, including ClipFace, dreamFace, TG-3dFace, and E3-FaceNet. We discuss their unique features, advantages, limitations, and the innovative techniques they employ to bridge the gap between natural language and 3d visual space. We also highlight the challenges that remain, such as achieving high fidelity and efficiency in the rendering process, and the potential for future advancements in this domain.

关键词： Surveys Solid modeling visualization Three-dimensional displays Computational modeling Natural languages Transforms

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共155页 << < 19 20 21 22 23 24 25 26 27 28 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：