检索结果-内蒙古大学图书馆

21st International Symposium on Vision, Modeling and visualization, VMV 2016

作者： Günther, Tobias Theisel, Holger Computer Graphics Laboratory ETH Zurich Switzerland Visual Computing Group University of Magdeburg Germany

ISBN: (纸本)9783038680253

Inertial particles are finite-sized objects that are carried by flows, for example sand particles in air. In contrast to massless tracer particles, the trajectories of inertial particles can intersect in space-time. When this occurs, the inertial flow map gradient becomes singular. This has an impact on visualization concepts that require the flow map gradient to be invertible. An example are influence curves, which allow to move inertial particles backward in time and thereby avoid the numerically ill-posed inertial backward integration. In this paper, we show that singularities of the inertial flow map gradient can act as poles for influence curves, i.e., as structures that influence curves cannot cross. Influence curves thereby decay into disconnected pieces. We extract singularities in space-time and propose a simple approach to extract influence curves even when they are spatially disconnected. We demonstrate the extraction techniques and discuss the role of singularities in a number of 2D vector fields. © 2016 The Author(s) Eurographics Proceedings © 2016 The Eurographics Association.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Photo-realistic 3D head modeling using multi-view images

引用

International Conference on Computational Science and its Applications, ICCSA 2004

作者： Lee, Tong-Yee Lin, Ping-Hsien Yang, Tz-Hsien Computer Graphics Group/Visual System Lab Department of Computer Science and Information Engineering National Cheng-Kung University Tainan Taiwan

ISBN: (纸本)3540220569

In this paper, we present a system for reconstructing photorealistic 3D head models from multi-view images. In the proposed system, we perform two-pass bundle adjustments to reconstruct a photo-realistic 3D head model. At the first pass it computes several feature points of a target 3D head and then use these features to modify a generic head to obtain a rough head model. Next, we perform the second pass bundle adjustment to compute a detailed 3D head model. The texture of head models is obtained from multi-views. After texturing on the reconstructed head models, several preliminary results of photo-realistic 3D head models are demonstrated to verify the proposed system. © Springer-Verlag Berlin Heidelberg 2004.

关键词： Three dimensional computer graphics

来源：评论

学校读者我要写书评

暂无评论

Texture Synthesis with Prioritized Pixel Re-synthesis

引用

Journal of Information Science and Engineering 2009年第2期25卷 389-402页

作者：嚴崇仁李同益 Computer Graphics Group/Visual System Laboratory Department of Computer Science and Information Engineering National Cheng Kung University

In this paper, we propose a new patch-based texture synthesis method. The core of the proposed method consists of two main components: (1) a feature-weighted similarity measurement to search for the best match and (2) a dynamically prioritized-based pixel re-synthesis to reduce discontinuity at the boundary of adjacent patches. Examples and experimental comparisons with other previous methods are demonstrated to verify the usefulness of our proposed method. In addition, we enhance the proposed method with a view warping technique to better synthesize non-frontal-parallel textures (NFPTs) that can not be synthesized well by traditional texture synthesis methods.

关键词： patch-based texture synthesis, prioritized-based pixel re-synthesis, feature- weighted, best match, discontinuity, frontal-parallel (FP) and non-frontal-parallel (NFP), view-warping

来源：评论

学校读者我要写书评

暂无评论

A novel semi-blind-and-semi-reversible robust watermarking scheme for 3D polygonal models

A novel semi-blind-and-semi-reversible robust watermarking s...

引用

作者： Lin, Chao-Hung Chao, Min-Wen Liang, Chan-Yu Lee, Tong-Yee Department of Geomatics National Cheng-Kung University No. 1 Ta-Hsueh Road Tainan 701 Taiwan Computer Graphics Group/Visual System Laboratory Department of Computer Science and Information Engineering National Cheng-Kung University No. 1 Ta-Hsueh Road Tainan 701 Taiwan

We introduce a novel semi-blind-and-semireversible robust watermarking scheme for three-dimensional (3D) polygonal models. The proposed approach embeds watermarks in the significant features of 3D models in a spread-spectrum manner. This novel scheme is robust against a wide variety of attacks including rotation, translation, scaling, noise addition, smoothing, mesh simplifications, vertex reordering, cropping, and even pose deformation of meshes. To the best of our knowledge, the existing approaches including blind, semi-blind, and non-blind detection schemes cannot withstand the attack of pose editing, which is a very common routine in 3D animation. In addition, the watermarked models can be semi-reversed (i.e., the peak signal-to-noise ratio (PSNR) of the recovered models is greater than 90 dB in all experiments) in semi-blind detection scheme. Experimental results show that this novel approach has many significant advantages in terms of robustness and invisibility over other state-of-the-art approaches. © Springer-Verlag 2010.

关键词： Watermarking

来源：评论

学校读者我要写书评

暂无评论

WYSIWYG: Mesh Decomposition for Static Models

WYSIWYG: Mesh Decomposition for Static Models

引用

International Conference on Intelligent Information Hiding and Multimedia Signal Processing (IIHMSP)

作者： Yu-Shuen Wang Tong-Yee Lee Computer Graphics Group/Visual System Lab National Cheng Kung University Tainan Taiwan

ISBN: (纸本)9780769529943;0769529941

Mesh decomposition plays an important role in computer graphics. However, the requirements for each of these applications demand the mesh decomposition process differently and therefore various decomposition schemes were developed as an end result. In this paper, we propose a flexible "WYSIWYG" (i.e. what you specify is what you get) decomposition algorithm for static meshes.

关键词： computer graphics Mesh generation Facial animation visual system Application software Partitioning algorithms Smoothing methods Shape

来源：评论

学校读者我要写书评

暂无评论

AssemblyNet: A Point Cloud Dataset and Benchmark for Predicting Part Directions in an Exploded Layout

AssemblyNet: A Point Cloud Dataset and Benchmark for Predict...

引用

IEEE Workshop on Applications of computer Vision (WACV)

作者： Jesper Gaarsdal Joakim Bruslund Haurum Sune Wolff Claus Brøndgaard Madsen SynergyXR ApS Aarhus Denmark Computer Graphics Group Aalborg University Denmark Visual Analysis and Perception (VAP) Laboratory Aalborg University & Pioneer Centre for AI Denmark

Exploded views are powerful tools for visualizing the assembly and disassembly of complex objects, widely used in technical illustrations, assembly instructions, and product presentations. Previous methods for automating the creation of exploded views are either slow and computationally costly or compromise on accuracy. Therefore, the construction of exploded views is typically a manual process. In this paper, we propose a novel approach for automatically predicting the direction of parts in an exploded view using deep learning. To achieve this, we introduce a new dataset, AssemblyNet, which contains point cloud data sampled from 3D models of real-world assemblies, including water pumps, mixed industrial assemblies, and LEGO models. The AssemblyNet dataset includes a total of 44 assemblies, separated into 495 subassemblies with a total of 5420 parts. We provide ground truth labels for regression and classification, representing the directions in which the parts are moved in the exploded views. We also provide performance benchmarks using various state-of-the-art models for shape classification on point clouds and propose a novel two-path network architecture. Project page available at https://***/jgaarsdal/AssemblyNet

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning to find good correspondences

arXiv

引用

arXiv 2017年

作者： Yi, Kwang Moo Trulls, Eduard Ono, Yuki Lepetit, Vincent Salzmann, Mathieu Fua, Pascal Visual Computing Group University of Victoria Computer Vision Laboratory École Polytechnique Fédérale de Lausanne Sony Imaging Products and Solutions Inc. Institute for Computer Graphics and Vision Graz University of Technology

We develop a deep architecture to learn to find good cor-respondences for wide-baseline stereo. Given a set of pu-tative sparse matches and the camera intrinsics, we train our network in an end-to-end fashion to label the corre-spondences as inliers or outliers, while simultaneously us-ing them to recover the relative pose, as encoded by the essential matrix. Our architecture is based on a multi-layer perceptron operating on pixel coordinates rather than di-rectly on the image, and is thus simple and small. We intro-duce a novel normalization technique, called Context Nor-malization, which allows us to process each data point sep-arately while embedding global information in it, and also makes the network invariant to the order of the correspon-dences. Our experiments on multiple challenging datasets demonstrate that our method is able to drastically improve the state of the art with little training data. Copyright © 2017, The Authors. All rights reserved.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Animation Generation and Retargeting Based on Physics Characteristics

Animation Generation and Retargeting Based on Physics Charac...

引用

International Conference on Intelligent Information Hiding and Multimedia Signal Processing (IIHMSP)

作者： Yao-Yang Tsai Hung-Kuo Chu Kuangyou B. Cheng Tong-Yee Lee Chen-Lan Yen Computer Graphics Group/Visual System Lab National Cheng Kung University Taiwan Institute of Physical Education Health and Leisure Studies National Cheng Kung University Taiwan Industrial Technology and Research Institute Tainan Taiwan

ISBN: (纸本)9780769529943;0769529941

Motion retargeting can be achieved by direct shape deformation transfer but may be visually unrealistic and physically incorrect. The purpose of this study is to include the consideration of physical properties for more realistic target motion synthesis. After partitioning source and target objects into segments, each segment mass and center of mass (COM) position/velocity are estimated. The target animation is generated by minimizing the difference in total linear momentum between source and target. Weighting functions for addressing the importance of segment motion and constraints on unrealistic segment length/velocity are also included. The results show that target movement amplitude and velocity are generally smaller than those of the source animation and with less seemly unrealistic motion. Thus, plausible animation can be generated by the retargeting procedures proposed in this study. The same methods may be applied to a variety of different target models for realistic motion synthesis.

关键词： Animation Character generation computer graphics Humans visual system computer science education Physics education computer industry Educational technology Shape

来源：评论

学校读者我要写书评

暂无评论

Vision-based Unmanned Aerial Vehicle detection and tracking for sense and avoid systems

Vision-based Unmanned Aerial Vehicle detection and tracking ...

引用

IEEE/RSJ International Conference on Intelligent Robots and systems

作者： Krishna Raj Sapkota Steven Roelofsen Artem Rozantsev Vincent Lepetit Denis Gillet Pascal Fua Alcherio Martinoli Computer Vision Laboratory School of Communication and Computer Sciences école Polytechnique Fédérale de Lausanne (EPFL) Switzerland Distributed Intelligent Systems and Algorithms Laboratory School of Architecture Civil and Environmental Engineering EPFL Switzerland Institute for Computer Graphics and Vision TU Graz Austria Coordination and Interaction System Group School of Engineering EPFL Switzerland

ISBN: (纸本)9781509037636

We propose an approach for on-line detection of small Unmanned Aerial Vehicles (UAVs) and estimation of their relative positions and velocities in the 3D environment from a single moving camera in the context of sense and avoid systems. This problem is challenging both from a detection point of view, as there are no markers on the targets available, and from a tracking perspective, due to misdetection and false positives. Furthermore, the methods need to be computationally light, despite the complexity of computer vision algorithms, to be used on UAVs with limited payload. To address these issues we propose a multi-staged framework that incorporates fast object detection using an AdaBoost-based approach, coupled with an on-line visual-based tracking algorithm and a recent sensor fusion and state estimation method. Our framework allows for achieving real-time performance with accurate object detection and tracking without any need of markers and customized, high-performing hardware resources.

关键词： Target tracking Object detection Collision avoidance Cameras visualization Detectors

来源：评论

学校读者我要写书评

暂无评论

Real virtual environment applications - Now 3

Real virtual environment applications - Now

引用

3rd Conference on visualization, VIS 1992

作者： Breen, Paul T. Grinstein, Georges G. Mizell, David W. Satava, Richard M. Smith, Bradford Stephens, Michael M. Zeltzer, David Department Head Applied Technology MITRE Corporation BedfordMA United States Continental C3 MITRE Corporation BedfordMA United States Institute for Visualization and Perception Research Computer Science Department University of Massachusetts Lowell LowellMA United States Computing Systems and Environments Boeing Computer Services SeattleWA United States General Surgery Silas B. Hays Army Hospital Fort OrdCA United States University of San Francisco BerkeleyCA United States System Engineering Division Computer Sciences Corporation VicksburgMS United States Computer Graphics and Animation Group Media Laboratory Massachusetts Institute of Technology CambridgeMA United States

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：