检索结果-内蒙古大学图书馆

Distortion Optimization based Image Completion from a Large Displacement View

computer graphics FORUM 2008年第7期27卷 1755-1764页

作者： Liu, Chunxiao Yang, Yingzhen Peng, Qunsheng Wang, Jin Chen, Wei Zhejiang Univ State Key Lab CAD&CG Hangzhou Zhejiang Peoples R China

We present a new image completion method based on an additional large displacement view (LDV) of the same scene for faithfully repairing large missing regions on the target image in an automatic way. A coarse-to-fine distortion correction algorithm is proposed to minimize the perspective distortion in the corresponding parts for the common scene regions on the LDV image. First, under the assumption of a planar scene, the LDV image is warped according to a homography to generate the initial correction result. Second, the residual distortions in the common known scene regions are revealed by means of a mismatch detection mechanism and relaxed by energy optimization of overlap correspondences, with the expectations of color constancy and displacement field smoothness. The fundamental matrix for the two views is then computed based on the reliable correspondence set. Third, under the constraints of epipolar geometry, displacement field smoothness and color consistency of the neighboring pixels, the missing pixels are orderly restored according to a specially defined repairing priority function. We finally eliminate the ghost effect between the repaired region and its surroundings by Poisson image blending. Experimental results demonstrate that our method outperforms recent state-of-the-art image completion methods for repairing large missing area with complex structure information.

关键词： I.3.3 [computer graphics]: Picture/Image Generation – Bitmap and Framebuffer Operations I.4.8 [Image Processing and computer Vision]: Scene Analysis - Stereo

来源：评论

学校读者我要写书评

暂无评论

Illuminating image-based objects

Illuminating image-based objects

引用

pacific conference on computer graphics and applications

作者： Tien-Tsin Wong Pheng-Ann Heng Siu-Hang Or Wai-Yin Ng Department of Computer Science & Engineering Chinese University of Hong Kong Hong Kong China Department of Information Engineering Chinese University of Hong Kong Hong Kong China

ISBN: (纸本)0818680288

We present a new scheme of data representation for image-based objects. It allows the illumination to be changed interactively without knowing any geometrical information (e.g. depth or surface normal) of the scene, but the resulting images are physically correct. The scene is first sampled from different view points and under different illuminations. By treating each pixel on the image plane as a surface element, the sampled images are used to measure the apparent BRDF of each surface element. Two compression schemes, spherical harmonics and discrete cosine transform, are proposed to compress the tabular BRDF data. Whenever the user changes the illumination a certain number of views are reconstructed. The correct user perspective view is then displayed using the standard texture mapping hardware. Hence, the intensity, the type and the number of the light sources can be manipulated interactively.

关键词： Lighting Surface treatment Layout Surface reconstruction Image coding Pixel Discrete cosine transforms Image reconstruction Hardware Light sources

来源：评论

学校读者我要写书评

暂无评论

Multi-dimensional transfer functions for interactive 3D flow visualization

Multi-dimensional transfer functions for interactive 3D flow...

引用

pacific conference on computer graphics and applications

作者： S.W. Park B. Budge L. Linsen B. Hamann K.I. Joy Department of Computer Science University of California Davis CA U.S.A

Transfer functions are a standard technique used in volume rendering to assign color and opacity to a volume of a scalar field. Multidimensional transfer functions (MDTFs) have proven to be an effective way to extract specific features with subtle properties. As 3D texture-based methods gain widespread popularity for the visualization of steady and unsteady flow field data, there is a need to define and apply similar MDTFs to interactive 3D flow visualization. We exploit flow field properties such as velocity, gradient, curl, helicity, and divergence using vector calculus methods to define an MDTF that can be used to extract and track features in a flow field. We show how the defined MDTF can be applied to interactive 3D flow visualization by combining them with state-of-the-art texture-based flow visualization of steady and unsteady fields. We demonstrate that MDTFs can be used to help alleviate the problem of occlusion, which is one of the main inherent drawbacks of 3D texture-based flow visualization techniques. In our implementation, we make use of current graphics hardware to obtain interactive frame rates.

关键词： Transfer functions Data visualization graphics Hardware Feature extraction Data mining Calculus Rendering (computer graphics) Data analysis computer science

来源：评论

学校读者我要写书评

暂无评论

Salient Region of Textured 3D Model

Salient Region of Textured 3D Model

引用

pacific conference on computer graphics and applications

作者： Bailin Yang Xun Wang Frederick W.B. Li College of Computer Science & Information Engineering Zhejiang Gongshang University Hangzhou China School of Engineering and Computing Sciences University of Durham UK

In this paper, we propose a salient region detection method for textured 3D models. We define the salient region, not only based on geometry properties, such as mean curvature, but also based on texture properties, such as texture color. Feature maps of geometry and texture are combined to form a saliency map for capturing the visually important regions of a textured 3D model. During the feature maps construction, we apply a novel filter window to obtain proper sample vertices and texels from the 3D geometry domain and 2D texture image domain. Given the saliency map, we have developed a model reduction method, which comprises the geometry simplification mechanism and the texture space optimization mechanism. Experimental results show that the salient regions of a model can be well preserved even if the model texture and geometry are simplified heavily.

关键词： Geometry Three dimensional displays Solid modeling Computational modeling Image color analysis Feature extraction Visualization

来源：评论

学校读者我要写书评

暂无评论

Representing Progressive Dynamic 3D Meshes and applications

Representing Progressive Dynamic 3D Meshes and Applications

引用

pacific conference on computer graphics and applications

作者： Chi-Kang Kao Bin-Shyan Jong Tsong-Wuu Lin Department of Electronic Engineering Taiwan Department of Information & Computer Engineering Taiwan Department of Computer and Information Science Taiwan

Dynamic 3D mesh sequences, also called 3D animation, have been widely used in the movie and gaming industries. However, the huge storage requirements of dynamic mesh data make it problematic for a number of applications such as rendering, transmission over a network, and displaying on mobile devices. This paper proposes a multi resolution representation of 3D animation that results displaying 3D animation progressively. The proposed method transforms traditional 3D animation representation into progressive representation, which takes up less storage and memory space. The progressive representation is constructed by compressing the animation into a base animation with sequenced refining operators. The base animation is viewable and can be reconstructed by transmitting for only a few seconds, which is also called thumbnail animation in this paper, the more detailed animation can be refined smoothly with applying refining operators. As the results, the resolution of animation can be free to change at real-time, where the resolution can be increased automatically or even controlled by user. Moreover, the progressive animation is more suitable for transmitting and displaying through the network.

关键词： Animation Geometry Decoding Principal component analysis Three dimensional displays Image coding Copper

来源：评论

学校读者我要写书评

暂无评论

Computing distances between surfaces using line geometry

Computing distances between surfaces using line geometry

引用

pacific conference on computer graphics and applications

作者： Kyung-Ah Sohn B. Juttler Myung-Soo Kim Wenping Wang School of Computer Science and Engineering Seoul National University South Korea Institute of Analysis Department of Applied Geometry Johannes Kepler University Linz Austria Department of Computer Science and Information Systems University of Hong Kong China

ISBN: (纸本)0769517846

We present an algorithm for computing the distance between two free-form surfaces. Using line geometry, the distance computation is reformulated as a simple instance of a surface-surface intersection problem, which leads to low-dimensional root finding in a system of equations. This approach produces an efficient algorithm for computing the distance between two ellipsoids, where the problem is reduced to finding a specific solution in a system of two equations in two variables. Similar algorithms can be designed for computing the distance between an ellipsoid and a simple surface (such as cylinder cone, or torus). In an experimental implementation (on a 500 MHz Windows PC), the distance between two ellipsoids was computed in less than 0.3 msec on average; and the distance between an ellipsoid and a simple convex surface was computed in less than 0.15 msec on average.

关键词： Computational geometry Equations Ellipsoids Biology computing Irrigation Testing Chromium computer science Engine cylinders Application software

来源：评论

学校读者我要写书评

暂无评论

A multiscale deformable model for extracting complex surfaces from volume images

A multiscale deformable model for extracting complex surface...

引用

pacific conference on computer graphics and applications

作者： Joo-Young Park T. McInerney D. Terzopoulos Myoung-Hee Kim Department of Computer Science and Engineering Ewha Womans University Seoul South Korea Department of Computer Science University of Toronto Toronto Canada

Deformable surface models are an attractive method for segmenting the three-dimensional shapes of complex anatomic structures in volumetric medical images. Despite the success of this approach, several problems remain. In this paper, we propose a multiscale deformable surface model with non-intersection constraint forces that successfully addresses three significant problems-sensitivity to model initialization, difficulties in dealing with severe object concavities, and model self-intersection. The first two problems are addressed by the multiscale scheme, which progressively resamples the triangulated, deformable surface model both globally and locally, matching its resolution to the levels of a volume image pyramid. We address the third problem by including a non-intersection constraint force among the customary internal and external forces in the physics-based formulation. We apply our new deformable surface model to the challenging task of extracting brain cortical surfaces.

关键词： Deformable models Image segmentation computer science Biomedical imaging Electronic switching systems Brain modeling Integrated circuit modeling Physics Solid modeling Image resolution

来源：评论

学校读者我要写书评

暂无评论

Multifunction workstation integrated voice/data/graphics for the ISDN environment

Multifunction workstation integrated voice/data/graphics for...

引用

IEEE pacific Rim conference on Communications, computers and Signal Processing

作者： Chewei Huang Guangguo Bi Qixiu Chen Li Li South-East University Nanjing China Nanjing Aeronautical Institute Nanjing China University of Ottawa Ottawa Canada

The authors focus on the development of a multifunction workstation for the ISDN environment, integrating voice, data, and graphics information. The configuration and services of the workstation are introduced. The multimedia protocol and multimedia synchronization are discussed, and the implementation of the ISDN communication control unit (CCU) board and the CCU interface to the host computer are described. In addition, a brief discussion is included on how to counteract weakness of the multitasking operation system in read-time support. The architecture and implementation of the basic system software and the relationship between parallel processes are described. Some applications of multifunction workstations are introduced.< >

关键词： Workstations ISDN computer graphics Protocols Communication system control computer interfaces Multitasking computer architecture System software Application software

来源：评论

学校读者我要写书评

暂无评论

Dataflow specification for system level synthesis of 3D graphics applications

Dataflow specification for system level synthesis of 3D grap...

引用

Asia and South pacific Design Automation conference

作者： Chanik Park Sungchan Kim Soonhoi Ha Computer Science and Engineering Seoul National University Seoul South Korea

ISBN: (纸本)0780366336

3D graphics is becoming an important application area together with multimedia applications. The dynamic behavior of 3D graphics application brings new challenges for system level specification and synthesis methodologies. Although existing dataflow models are successfully used for DSP system design, they are not sufficient to deal with 3D graphics algorithms since they are lacking in global state management and dynamic behavior handling. In this paper, we propose an extended synchronous piggybacked dataflow model with dynamic constructs for representing 3D graphics algorithm. We also present implementation techniques for software and hardware synthesis from the specification. With a simple 3D graphics pipeline, we show the novelty and usefulness of the proposed specification model.

关键词： Pipelines Application software Digital signal processing System-level design computer graphics Hardware Formal specifications computer science Electronic mail Power system modeling

来源：评论

学校读者我要写书评

暂无评论

A signal processing approach to feature edge extraction in mesh surfaces

A signal processing approach to feature edge extraction in m...

引用

conference on Vision Geometry XI

作者： Jang, HN Agam, G IIT Dept Comp Sci Chicago IL 60616 USA

ISBN: (纸本)0819445614

Mesh surfaces are an important form of 3D object representation which has become increasingly significant in recent years due to evolving 3D acquisition techniques, computing power, and commercial needs. Feature edge extraction in polygonal meshes has numerous applications ranging from scene segmentation and object recognition to mesh compression. The method proposed in this paper for feature edge extraction in polygonal mesh surfaces follows the signal processing approach to edge detection in images at multiple scales and in the presence of noise. Namely, multiple smoothing iterations in the spatial domain are used to produce several versions of the original mesh at different scales, whereas the same topology is maintained throughout the scales. Edges are extracted at each scale by applying a differential operator to an underlying locally smooth surface represented by the mesh at that scale so as to evaluate the curvature at each vertex of the mesh. The proposed approach is based on the identification of multiple local support planes that facilitate the representation of an arbitrary mesh surface by a set of overlapping Monge patches. Such a representation enables the application of curvature estimation techniques commonly employed for range image analysis, and provides an alternative to Laplacian smoothing by local quadratic surface fitting. The proposed approach is suitable for irregular and non-dense meshes.

关键词： mesh surfaces mesh smoothing curvature estimation feature edge detection computer vision computer graphics

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：