检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Chen, Lan Gao, Lin Yang, Jie Xu, Shibiao Ye, Juntao Zhang, Xiaopeng Lai, Yu-Kun Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Beijing Key Laboratory of Mobile Computing and Pervasive Device China Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences Beijing China Institute of Automation Chinese Academy of Sciences Beijing China Visual Computing Group School of Computer Science and Informatics Cardiff University Wales United Kingdom

In physics-based cloth animation, rich folds and detailed wrinkles are achieved at the cost of expensive computational resources and huge labor tuning. Data-driven techniques make efforts to reduce the computation significantly by utilizing a preprocessed database. One type of methods relies on human poses to synthesize fitted garments, but these methods cannot be applied to general cloth animations. Another type of methods adds details to the coarse meshes, which does not have such restrictions. However, existing works usually utilize coordinate-based representations which cannot cope with large-scale deformation, and requires dense vertex correspondences between coarse and fine meshes. Moreover, as such methods only add details, they require coarse meshes to be sufficiently close to fine meshes, which can be either impossible, or require unrealistic constraints to be applied when generating fine meshes. To address these challenges, we develop a temporally and spatially as-consistent-as-possible deformation representation (named TS-ACAP) and design a DeformTransformer network to learn the mapping from low-resolution meshes to ones with fine details. This TS-ACAP representation is designed to ensure both spatial and temporal consistency for sequential large-scale deformations from cloth animations. With this TS-ACAP representation, our DeformTransformer network first utilizes two mesh-based encoders to extract the coarse and fine features using shared convolutional kernels, respectively. To transduct the coarse features to the fine ones, we leverage the Transformer network that consists of frame-level attention mechanisms to ensure temporal coherence of the prediction. Experimental results show that our method is able to produce reliable and realistic animations in various datasets at high frame rates: 10 ∼ 35 times faster than physics-based simulation, with superior detail synthesis abilities compared to existing methods. Copyright © 2021, The Authors. All rights r

关键词： Deformation

来源：评论

学校读者我要写书评

暂无评论

A Framework for 3D Reconstruction Dataset Preprocessing

A Framework for 3D Reconstruction Dataset Preprocessing

引用

International Conference on Virtual Reality and visualization (ICVRV)

作者： Xinyu Wang Xun Luo Mingtian Yu Chu Shi Yunrui Zhu Chen Gong Pervasive and Visual Computing Group Tianjin University of Technology Tianjin China Tianjin University of Technology

ISBN: (数字)9781728147529

ISBN: (纸本)9781728147536

In order to improve the efficiency and effect of outdoor 3d reconstruction, we designed this image set preprocessing system, which can screen out some pictures that do not meet the requirements and are of low quality through screening the blur degree, exposure degree and jitter degree of UAV aerial photo set. Using filtered photo sets can greatly reduce the impact of low-quality images on modeling speed and quality.

关键词： Conferences Virtual reality visualization

来源：评论

学校读者我要写书评

暂无评论

Multiscale mesh deformation component analysis with attention-based autoencoders

arXiv

引用

arXiv 2020年

作者： Yang, Jie Gao, Lin Tan, Qingyang Huang, Yihua Xia, Shihong Lai, Yu-Kun Beijing Key Laboratory of Mobile Computing and Pervasive Device Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences Beijing China University of Maryland College ParkMD United States Visual Computing Group School of Computer Science and Informatics Cardiff University Wales United Kingdom

Deformation component analysis is a fundamental problem in geometry processing and shape understanding. Existing approaches mainly extract deformation components in local regions at a similar scale while deformations of real-world objects are usually distributed in a multi-scale manner. In this paper, we propose a novel method to exact multiscale deformation components automatically with a stacked attention-based autoencoder. The attention mechanism is designed to learn to softly weight multi-scale deformation components in active deformation regions, and the stacked attention-based autoencoder is learned to represent the deformation components at different scales. Quantitative and qualitative evaluations show that our method outperforms state-of-the-art methods. Furthermore, with the multiscale deformation components extracted by our method, the user can edit shapes in a coarse-to-fine fashion which facilitates effective modeling of new shapes. Copyright © 2020, The Authors. All rights reserved.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Human Motion Transfer with 3D Constraints and Detail Enhancement

arXiv

引用

arXiv 2020年

作者： Sun, Yang-Tian Fu, Qian-Cheng Jiang, Yue-Ren Liu, Zitao Lai, Yu-Kun Fu, Hongbo Gao, Lin Beijing Key Laboratory of Mobile Computing and Pervasive Device Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Department of Computer Science Boston University United States Guangdong Institute of Smart Education Jinan University Guangzhou China Visual Computing Group School of Computer Science and Informatics Cardiff University Wales United Kingdom School of Creative Media City University of Hong Kong Hong Kong

We propose a new method for realistic human motion transfer using a generative adversarial network (GAN), which generates a motion video of a target character imitating actions of a source character, while maintaining high authenticity of the generated results. We tackle the problem by decoupling and recombining the posture information and appearance information of both the source and target characters. The innovation of our approach lies in the use of the projection of a reconstructed 3D human model as the condition of GAN to better maintain the structural integrity of transfer results in different poses. We further introduce a detail enhancement net to enhance the details of transfer results by exploiting the details in real source frames. Extensive experiments show that our approach yields better results both qualitatively and quantitatively than the state-of-the-art methods. Copyright © 2020, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Implementation of VR Scene of Sino-US Innovation Exchange Center

Implementation of VR Scene of Sino-US Innovation Exchange Ce...

引用

International Conference on Virtual Reality and visualization (ICVRV)

作者： Danning Ma Xun Luo Cheng Ye Wenzhe Zhang Cheng Shan Pervasive and Visual Computing Group Tianjin University of Technology Tianjin China

ISBN: (纸本)9781538684986;9781538684979

As a scenario experience project running on PC, this work takes roaming the Innovation and Entrepreneurship Education Center of the Department of Psychology of Beijing Normal University as the background, and takes the real scene inside the education center as the prototype, so that visitors can experience the roaming realized by virtual reality technology.

关键词： Conferences Virtual reality visualization

来源：评论

学校读者我要写书评

暂无评论

A Roaming Game in 3D Reconstructed Campus

A Roaming Game in 3D Reconstructed Campus

引用

International Conference on Virtual Reality and visualization (ICVRV)

作者： Yunrui Zhu Xun Luo Rui Gao Yuan Wang Chu Shi Pervasive and Visual Computing Group Tianjin University of Technology Tianjin China

ISBN: (纸本)9781538684986;9781538684979

This work is based on the campus of Tianjin University of Technology. It uses 3D reconstruction technology to build its 3D virtual scene. Then, use the Unreal Engine Unreal Engine to use blueprints, mixed spaces, animation montages, etc. to realize the three roaming modes of characters, vehicles and helicopters. Allowing visitors to experience the roaming campus realized by virtual reality technology. Promote campus culture in a unique way and increase campus awareness.

关键词： Conferences Virtual reality visualization

来源：评论

学校读者我要写书评

暂无评论

How Parallelization Helps Crowd Simulation: Study of an OpenMP-Based System

How Parallelization Helps Crowd Simulation: Study of an Open...

引用

International Conference on Virtual Reality and visualization (ICVRV)

作者： Edwin Lobo-Hernández Xun Luo Gustavo Alomía-Peñafiel Nan Liu Claudia Zúñiga-Cañón Research Group COMBA R & D University of Santiago de Cali Cali Colombia Pervasive and Visual Computing Group Tianjin University of Technology Tianjin China Universidad Santiago de Cali Cali CO

This paper analyzes the parallelization efficiency of Menge [1], an open source virtual crowd simulation system widely used for algorithm benchmarking, with focuses on three aspects: performance of the existing parallel processing scheme, bottleneck of parallel processing, and improvement opportunities for parallel efficiency of the system. First, we calculate the speedup ratio of each Menge module by analyzing the data collected under with and without OpenMP scenarios. We then identify the bottleneck of the parallel computing from the empirical study. Secondly, the possibility of improving the performance through hardware configuration is analyzed by testing the performance of the system on different computers which have the similar clock frequencies but different number of cores. The experimental results show that there is still plenty of room for improvement in the parallelization performance of the system.

关键词： Computational modeling Central Processing Unit Parallel processing Computers Solid modeling Program processors Collision avoidance

来源：评论

学校读者我要写书评

暂无评论

From Great Wall to the Andes: Sino-Latin America Collaborations on Urban computing, Virtual Reality, and visualization Research

From Great Wall to the Andes: Sino-Latin America Collaborati...

引用

International Conference on Virtual Reality and visualization (ICVRV)

作者： Xun Luo Wei Wu Claudia Zúñiga-Cañón Carlos Lozano-Garzón Pervasive and Visual Computing Group Tianjin University of Technology Tianjin China State Key Lab on Virtual Reality Technology and Systems Beihang University Beijing China Research Group COMBA R&D Universidad Santiago de Cali Cali Colombia Systems and Computing Engineering Department Universidad de Los Andes Bogota Colombia

During the past couple years, several Chinese and Latin American research communities have established and strengthened notable collaborative ties, in the fields of urban computing, virtual reality and visualization. These endeavors culminate in 2016 as the Sino-Latin America Birds of a Feather (SLA-BOF) event at the International Conference on Virtual Reality and visualization (ICVRV). In this event chairs' report, we present overview of the history, status quo and ongoing initiatives about such collaborations. We encourage more institutions to join this international joint effort.

关键词： Virtual reality Collaboration visualization Urban areas Solid modeling Education Sensors

来源：评论

学校读者我要写书评

暂无评论

DaDDy: A Data Driven Dynamic Course Table Planner

DaDDy: A Data Driven Dynamic Course Table Planner

引用

International Conference on Virtual Reality and visualization (ICVRV)

作者： Efren Cando Narváez Xun Luo Zilong Zhang Geovanny Dalino Chavez Garcia Claudia Zúñiga-Cañón Escuela Politecnica Nacional Robotic and Intelligent Systems Laboratory Quito Ecuador Pervasive and Visual Computing Group Tianjin University of Technology Tianjin China Escuela Politec. Nac. Quito Robotic & Intell. Syst. Lab. Quito Ecuador Research Group COMBA R & D University of Santiago de Cali Cali Colombia

Crowd simulation technologies and systems can show and tell a lot of insights on massive crowds' movement behavior. Benefiting from such characteristics, they have found themselves useful in many application fields. On the other hand, a typical educational institution, such as university, has a large body of student population, whose course schedules dominate their daily movement patterns. How to arrange courses according to the school resource of building vacancy and road availability is thus an important problem to be solved by administrators. Traditional ways of arranging course tables are solely based on the consideration of faculty and students schedule availability, often causing road congestions on campus. Furthermore, such arrangements may not be optimized for emergency situations, under which student crowds need to be evacuated. Enlightened by these observations, we designed and implemented a system dubbed as DaDDy Planner (Data Driven Dynamic Planner) which allows school administrators to compare multiple planning solutions of course table visually. Our system makes use of crow simulation and shows advantage in usability as well as efficiency.

关键词： Buildings Computational modeling Planning Roads Data models Cameras Detectors

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：