检索结果-内蒙古大学图书馆

15th International Workshop on Vision, Modeling and Visualization, VMV 2010

作者： Löffler, F. Schumann, H. University of Rostock Institute of Computer Science/Computer Graphics Germany

ISBN: (纸本)9783905673791

Terrain simplification generates multi-resolution models, from which - traditionally - irregular or semi-regular triangulations are extracted to render a terrain at a suitable level of detail. Recent terrain simplification techniques, in contrast, rely on GPU-friendly regular grids and generate multiple resolutions by applying the filtering and sub-sampling paradigm. However, due to the smoothing and uniform sampling, these techniques sparsely approximate the terrain surface. Consequently, in order to guarantee a certain error threshold, considerably more triangles need to be rendered. In this paper, we present a novel feature-sensitive simplification technique. Our approach follows the aforementioned paradigm. The key idea is to maintain the regularity while recomputing the vertex positions by taking a specific error metric into account, namely the quadric error metric (QEM). Compared to previous approaches, we apply the paradigm to the grid of vertex-associated quadrics. From these we extract vertices of the new resolution by relying on quadric error minimization. We, thus, maintain the regular grid structure while preserving terrain features. Compared to methods, which are solely based on vertex-filtering and sub-sampling, our approach reduces the approximation error. As a consequence, we require fewer triangles, which improves the rendering performance. © The Eurographics Association 2010.

关键词： Landforms

来源：评论

学校读者我要写书评

暂无评论

GPU-based appearance preserving trimmed NURBS rendering

GPU-based appearance preserving trimmed NURBS rendering

引用

14th International Conference in Central Europe on computer graphics, Visualization and computer Vision 2006, WSCG'2006 - In Co-operation with EUROgraphics

作者： Guthe, Michael Balázs, Ákos Klein, Reinhard Universitä Bonn Institute of Computer Science II Computer Graphics Römerstraße 164 53117 Bonn Germany

ISBN: (纸本)8086943038

Trimmed NURBS are the standard surface representation used in CAD/CAM systems and accurate visualization of trimmed NURBS models at interactive frame rates is of great interest for industry. To support modification and/or animation of such surfaces, a GPU-based trimming and tessellation algorithm has been developed recently. First, the NURBS is approximated with a bi-cubic hierarchy of Bezier patches on the CPU and then these are tessellated on the GPU. Since this approach only took the geometric error of an approximation into account, the various illumination artifacts introduced by the chosen bi-cubic approximation and the subsequent tessellation were neglected. Although this problem could be solved partially by calculating exact per-pixel normals on the GPU, the shading error introduced due to the bi-cubic approximation would remain. Furthermore, the long fragment shader required for per-pixel normals would lead to unacceptably low performance. In this paper we present a novel bi-cubic approximation algorithm that takes the normal approximation error into account. In addition, we also define a new error measure to calculate the required grid resolution for the bi-linear approximation. In combination, this allows GPU-based NURBS tessellation with guaranteed visual fidelity. Our new method is also capable of high quality visualization of further attributes like curvature, temperature, etc. on surfaces with little or no modification. Copyright © UNION Agency - science Press.

关键词： graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Compressed progressive meshes (vol 6, pg 79, 2000)

引用

IEEE TRANSACTIONS ON VISUALIZATION AND computer graphics 2000年第2期6卷 190-192页

作者： Pajarola, R Rossignac, J Information and Computer Science Department University of California Irvine Graphics Visualization and Usablity Center Georgia Institute of Technology

Most systems that support visual interaction with 3D models use shape representations based on triangle meshes. The size of these representations imposes limits on applications for which complex 3D models must be accessed remotely. Techniques for simplifying and compressing 3D models reduce the transmission time. Multiresolution formats provide quick access to a crude model and then refine it progressively. Unfortunately, compared to the best nonprogressive compression methods, previously proposed progressive refinement techniques impose a significant overhead when the full resolution model must be downloaded. The CPM (Compressed Progressive Meshes) approach proposed here eliminates this overhead. It uses a new technique, which refines the topology of the mesh in batches, which each increase the number of vertices by up to 50 percent. Less than an amortized total of 4 bits per triangle encode where and how the topological refinements should be applied. We estimate the position of new vertices from the positions of their topological neighbors in the less refined mesh using a new estimator that leads to representations of vertex coordinates that are 50 percent more compact than previously reported progressive geometry compression techniques.

关键词： Triangle mesh compression Progressive Meshes Multiresolution Modeling Geometry Compression

来源：评论

学校读者我要写书评

暂无评论

Either Or: Interactive Articles or Videos for Climate science Communication

引用

computer graphics Forum 2025年

作者： Poehls, J. Meuschke, M. Carvalhais, N. Lawonn, K. Max Planck Institute for Biogeochemistry Department of Biogeochemical Integration Germany University of Magdeburg Department of Simulation and Graphics Germany University of Jena Institute of Computer Science Germany

Effective communication of climate science is critical as climate-related disasters become more frequent and severe. Translating complex information, such as uncertainties in climate model predictions, into formats accessible to diverse audiences is key to informed decision-making and public engagement. This study investigates how different teaching formats can enhance understanding of these uncertainties. This study compares two multimodal strategies: (1) a text-image format with interactive components and (2) an explainer video combining dynamic visuals with narration. Participants' immediate and delayed retention (one week) and engagement are assessed to determine which format offers greater saliency. Sample analysis (n = 622) displayed equivalent retention by viewers between both formats. Metrics assessing interactivity found no correlation between interactivity and information retention. However, a stark contrast was observed in the time viewers spent engaging with each format. The video format was 29% more efficient with information taught over a period of time vs. the article. Additionally, retention on the video format worsened with age (P = 0.004) while retention on the article format improved with education (P = 0.038). These results align with previous findings in literature. © 2025 The Author(s). computer graphics Forum published by Eurographics - The European Association for computer graphics and John Wiley & Sons Ltd.

关键词： Signaling

来源：评论

学校读者我要写书评

暂无评论

Memory efficient billboard clouds for BTF textured objects

Memory efficient billboard clouds for BTF textured objects

引用

Vision, Modeling and Visualization 2004, VMV 2004

作者： Meseth, Jan Klein, Reinhard Institute for Computer Science II Computer Graphics Group University of Bonn Römerstr. 164 Bonn53117 Germany

ISBN: (纸本)3898380580

Efficiently rendering highly structured models distant from the viewer constitutes a difficult task since the geometric complexity has to be reduced extremely while simultaneously preserving the overall visual quality. Recently, billboard clouds have been introduced as an new solution to this problem. They achieve acceptable performance by coarsely approximating the geometry of a model while storing surface details as textures. Yet, important surface detail due to self-shadowing, reflectance properties and changing silhouettes is lost. In this paper we introduce Bidirectional Texture Function (BTF) textured billboard clouds which drastically increase the visual quality by preserving view- and light-dependent effects like reflection properties, changing silhouette and changing shadows while preserving the fast rendering performance. In order to utilize the gains of BTFs, we propose two new methods for generation of memory efficient billboard clouds optimized for connected and unconnected models that preserve the normals of the model much better than previous approaches.

关键词： Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

Multiresolution rendering by sewing trimmed NURBS surfaces

Multiresolution rendering by sewing trimmed NURBS surfaces

引用

Proceddings Seventh ACM Symposium on Solid Modeling and Applications SM'02

作者： Kahlesz, Ferenc Balázs, Ákos Klein, Reinhard University of Bonn Insitute of Computer Science II Computer Graphics Römerstrasse 164 53117 Bonn Germany

Most of the industrial parts are designed as trimmed NURBS. For their efficient rendering multiresolution models are needed. To create such models without artifacts at the trimming curves, one needs to sew parts together along the common boundaries. Due to the problem of determining the geometric places in 3D space along the trimming curves where sewing should be done, current approaches need to have a priori neighbourhood information of the patches and this way they do not provide an automatic solution to create large connected models just from a set of surfaces. In this paper we describe a method, which automatically determines common boundaries of trimmed NURBS surfaces and sews along them. Such a method provides us a non-manifold or manifold structures which can be handled using standard multi-resolution techniques. Several examples of industrial data demonstrate the efficiency and applicability of our new method. The introduced techniques will also be included into the OpenSG scenegraph API [8] as the basic tool for NURBS rendering.

关键词： computer aided design

来源：评论

学校读者我要写书评

暂无评论

ID-Booth: Identity-consistent Face Generation with Diffusion Models

arXiv

引用

arXiv 2025年

作者： Tomašević, Darian Boutros, Fadi Lin, Chenhao Damer, Naser Štruc, Vitomir Peer, Peter University of Ljubljana Faculty of Computer and Information Science Ljubljana Slovenia Fraunhofer Institute for Computer Graphics Research IGD Darmstadt Germany Xi’an Jiaotong University School of Cyber Science and Engineering Xi’an China University of Ljubljana Faculty of Electrical Engineering Ljubljana Slovenia

Recent advances in generative modeling have enabled the generation of high-quality synthetic data that is applicable in a variety of domains, including face recognition. Here, state-of-the-art generative models typically rely on conditioning and fine-tuning of powerful pretrained diffusion models to facilitate the synthesis of realistic images of a desired identity. Yet, these models often do not consider the identity of subjects during training, leading to poor consistency between generated and intended identities. In contrast, methods that employ identity-based training objectives tend to overfit on various aspects of the identity, and in turn, lower the diversity of images that can be generated. To address these issues, we present in this paper a novel generative diffusion-based framework, called ID-Booth. ID-Booth consists of a denoising network responsible for data generation, a variational auto-encoder for mapping images to and from a lower-dimensional latent space and a text encoder that allows for prompt-based control over the generation procedure. The framework utilizes a novel triplet identity training objective and enables identity-consistent image generation while retaining the synthesis capabilities of pretrained diffusion models. Experiments with a state-of-the-art latent diffusion model and diverse prompts reveal that our method facilitates better intra-identity consistency and inter-identity separability than competing methods, while achieving higher image diversity. In turn, the produced data allows for effective augmentation of small-scale datasets and training of better-performing recognition models in a privacy-preserving manner. The source code for the ID-Booth framework is publicly available at https://***/dariant/ID-Booth. Copyright © 2025, The Authors. All rights reserved.

关键词： Image coding

来源：评论

学校读者我要写书评

暂无评论

Weakly-Supervised Single-view Dense 3D Point Cloud Reconstruction via Differentiable Renderer

引用

Chinese Journal of Mechanical Engineering 2021年第5期34卷 195-205页

作者： Peng Jin Shaoli Liu Jianhua Liu Hao Huang Linlin Yang Michael Weinmann Reinhard Klein School of Mechanical Engineering Beijing Institute of TechnologyBeijing 100081China Institute of Computer Science II University of Bonn53115 BonnGermany

In recent years,addressing ill-posed problems by leveraging prior knowledge contained in databases on learning techniques has gained much *** this paper,we focus on complete three-dimensional(3D)point cloud reconstruction based on a single red-green-blue(RGB)image,a task that cannot be approached using classical reconstruction *** this purpose,we used an encoder-decoder framework to encode the RGB information in latent space,and to predict the 3D structure of the considered object from different *** individual predictions are combined to yield a common representation that is used in a module combining camera pose estimation and rendering,thereby achieving differentiability with respect to imaging process and the camera pose,and optimization of the two-dimensional prediction error of novel ***,our method allows end-to-end training and does not require supervision based on additional ground-truth(GT)mask annotations or ground-truth camera pose *** evaluation of synthetic and real-world data demonstrates the robustness of our approach to appearance changes and self-occlusions,through outperformance of current state-of-the-art methods in terms of accuracy,density,and model completeness.

关键词： Point clouds reconstruction Differentiable renderer Neural networks Single-view configuration

来源：评论

学校读者我要写书评

暂无评论

Animating turbulent water by vortex shedding in PIC/FLIP

引用

science China(Information sciences) 2013年第3期56卷 16-26页

作者： ZHU Jian LIU YouQuan CHANG YuanZhang WU EnHua Computer Graphics and Multimedia Laboratory(NG04) Faculty of Science and TechnologyUniversity of Macau School of Information Engineering Chang'an University State Key Laboratory of Computer Science Institute of SoftwareChinese Academy of Sciences

In this paper,we present a hybrid method,which integrates PIC/FLIP and vortex particle methods into a unified framework,to efficiently simulate vortex shedding that happens when fluids flow around internal *** improve efficiency and reduce the numerical dissipations,we first solve the governing equations on a coarse grid using PIC/FLIP,and then interpolate the intermediate results to a finer grid to obtain the base *** the regular particles in PIC/FLIP enter the boundary layer,if the specified conditions are satisfied to cause vortex shedding,they are selected as vortex particles by assigning additional vorticity related *** vortex particle dynamics are controlled by the vorticity form of NS equations,and several efficient methods are proposed to solve them on the finer ***,the obtained turbulence flow is added to the base *** a result,we are able to simulate turbulent water with rich wake details around the internal obstacles.

关键词： physically based fluid simulation turbulence vortex shedding vortex particle PIC/FLIP

来源：评论

学校读者我要写书评

暂无评论

Approximate merging of multiple Bézier segments

引用

Progress in Natural science:Materials International 2008年第6期18卷 757-762页

作者： Min Chenga,b,Guojin Wanga,* ainstitute of computer graphics and Image Processing,Zhejiang University,Hangzhou 310027,China bCollege of science,Zhejiang University of Technology,Hangzhou 310032,China Institute of Computer Graphics and Image Processing Zhejiang University Hangzhou 310027 China College of Science Zhejiang University of Technology Hangzhou 310032 China

This paper deals with the approximate merging problem of multiple adjacent Bézier curves with dierent degrees by a single Bézier curve,which is a frequently seen problem in *** unified matrix representation for precise merging is presented and the approx-imate merging curve is further derived based on matrix *** at the endpoints of curves is also discussed in the merging *** show that the method in this paper achieves satisfying merging results.

关键词： computer-aided geometric design Bézier curve Approximate merging Matrix representation

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：