检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Hänel, Tobias Kumar, Nishant Schlesinger, Dmitrij Li, Mengze Ünal, Erdem Eslami, Abouzar Gumhold, Stefan Computer Graphics and Visualization TU Dresden Germany Carl Zeiss Meditec AG Munich Germany

The performance of deep neural networks for image recognition tasks such as predicting a smiling face is known to degrade with under-represented classes of sensitive attributes. We address this problem by introducing fairness-aware regularization losses based on batch estimates of Demographic Parity, Equalized Odds, and a novel Intersection-over-Union measure. The experiments performed on facial and medical images from CelebA, UTKFace, and the SIIM-ISIC melanoma classification challenge show the effectiveness of our proposed fairness losses for bias mitigation as they improve model fairness while maintaining high classification performance. To the best of our knowledge, our work is the first attempt to incorporate these types of losses in an end-to-end training scheme for mitigating biases of visual attribute predictors. Our code is available at this https URL. © 2022, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Automatic tuning of liver tissue model using simulated annealing and genetic algorithm heuristic approaches

引用

AIP Conference Proceedings 2014年第1期1605卷 313-318页

作者： Salina Sulaiman Abdullah Bade Rechard Lee Siti Hasnah Tanalol Real-Time Computer Graphics and Visualization (GRAVS) School of Science and Technology Universiti Malaysia Sabah 88400 Kota Kinabalu Sabah Malaysia

Mass Spring Model (MSM) is a highly efficient model in terms of calculations and easy implementation. Mass, spring stiffness coefficient and damping constant are three major components of MSM. This paper focuses on identifying the coefficients of spring stiffness and damping constant using automated tuning method by optimization in generating human liver model capable of responding quickly. To achieve the objective two heuristic approaches are used, namely Simulated Annealing (SA) and Genetic Algorithm (GA) on the human liver model data set. The properties of the mechanical heart, which are taken into consideration, are anisotropy and viscoelasticity. Optimization results from SA and GA are then implemented into the MSM to model two human hearts, each with its SA or GA construction parameters. These techniques are implemented while making FEM construction parameters as benchmark. Step size response of both models are obtained after MSMs were solved using Fourth Order Runge-Kutta (RK4) to compare the elasticity response of both models. Remodelled time using manual calculation methods was compared against heuristic optimization methods of SA and GA in showing that model with automatic construction is more realistic in terms of realtime interaction response time. Liver models generated using SA and GA optimization techniques are compared with liver model from manual calculation. It shows that the reconstruction time required for 1000 repetitions of SA and GA is faster than the manual method. Meanwhile comparison between construction time of SA and GA model indicates that model SA is faster than GA with varying rates of time 0.110635 seconds/1000 repetitions. Real-time interaction of mechanical properties is dependent on rate of time and speed of remodelling process. Thus, the SA and GA have proven to be suitable in enhancing realism of simulated real-time interaction in liver remodelling.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Light Direction Reconstruction from single RGB images 29

Deep Light Direction Reconstruction from single RGB images

引用

29th International Conference in Central Europe on computer graphics, visualization and computer Vision, WSCG 2021

作者： Miller, Markus Nischwitz, Alfred Westermann, Rüdiger Dept. of Computer Science and Mathematics University of Applied Sciences Munich Lothstr. 64 Bavaria MunichD-80335 Germany Chair of Computer Graphics and Visualization Technical University Munich Boltzmannstr. 3/II Bavaria GarchingD-85748 Germany

ISBN: (纸本)9788086943343

In augmented reality applications, consistent illumination between virtual and real objects is important for creating an immersive user experience. Consistent illumination can be achieved by appropriate parameterisation of the virtual illumination model, that is consistent with real-world lighting conditions. In this study, we developed a method to reconstruct the general light direction from red-green-blue (RGB) images of real-world scenes using a modified VGG-16 neural network. We reconstructed the general light direction as azimuth and elevation angles. To avoid inaccurate results caused by coordinate uncertainty occurring at steep elevation angles, we further introduced stereographically projected coordinates. Unlike recent deep-learning-based approaches for reconstructing the light source direction, our approach does not require depth information and thus does not rely on special red-green-blue-depth (RGB-D) images as input. © 2021 University of West Bohemia. All rights reserved.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Particle-based fluid-fluid interaction 05

Particle-based fluid-fluid interaction

引用

Proceedings of the 2005 ACM SIGGRAPH/Eurographics symposium on computer animation

作者： Müller, Matthias Solenthaler, Barbara Keiser, Richard Gross, Markus NovodeX AG Zürich AGEIA Inc. St. Louis United States Visualization and Multimedia Lab. University of Zürich Switzerland Computer Graphics Lab. ETH Zürich Switzerland

ISBN: (纸本)9781595931986

The interesting and complex behavior of fluids emerges mainly from interaction processes. While interactions of fluids with static or dynamic solids has caught some attention in computer graphics lately, the mutual interaction of different types of fluids such as air and water or water and wax has received much less attention although these types of interaction are the basis for a variety of important phenomena. In this paper we propose a new technique to model fluid-fluid interaction based on the Smoothed Particle Hydrodynamics (SPH) method. For the simulation of air-water interaction, air particles are generated on the fly only where needed. We also model dynamic phase changes and interface forces. Our technique makes possible the simulation of phenomena such as boiling water, trapped air and the dynamics of a lava lamp. © 2010 ACM.

关键词： Air

来源：评论

学校读者我要写书评

暂无评论

The Lego interface toolkit 96

The Lego interface toolkit

引用

Proceedings of the 9th annual ACM symposium on User interface software and technology

作者： Matthew Ayers Robert Zeleznik Brown University site of the NSF Science and Technology Center for Computer Graphics and Scientific Visualization Providence RI

No abstract available.

ISBN: (纸本)9780897917988

No abstract available.

关键词： 3D interface virtual reality snap-together reconfigurable hardware Lego prototype

来源：评论

学校读者我要写书评

暂无评论

Teaching Distributed and Heterogeneous Robotic Cells 19

Teaching Distributed and Heterogeneous Robotic Cells

引用

19th IEEE Annual Consumer Communications and Networking Conference, CCNC 2022

作者： Mey, Johannes Ebert, Sebastian Lin, Tianfang Nguyen, Giang T. Gumhold, Stefan Asmann, Uwe Technische Universität Chair of Software Engineering Dresden Germany Technische Universität Chair of Computer Graphics and Visualization Dresden Germany Technische Universität Chair of Haptic Communication Systems Dresden Germany Dresden Germany

ISBN: (纸本)9781665431620

Teaching heterogeneous robotic cells is difficult and time-consuming. We present a context-aware robot teaching solution based on an open-source framework that decouples the task instruction from the task execution to simplify the teaching workflow significantly. To demonstrate the advantages of the solution, a human operator uses a VR headset and controllers to teach a virtual robot to perform a task, e.g., pick-and-place in a virtual world. The task is automatically adapted to different settings of operation cells and executed by physical robots located at different geographical locations. © 2022 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Multi-path algorithm for triangle strips

Multi-path algorithm for triangle strips

引用

computer graphics International

作者： P. Vanecek I. Kolingerova Centre of Computer Graphics and Data Visualization Department of Computer Science and Engineering University of West Bohemia Pilsen Czech Republic

Triangle surface models belong to the most popular type of geometric objects description in computer graphics. Therefore, the problem of fast visualization of this type of data is often solved. One of popular approaches is stripification, i.e., a conversion of triangle surface into strips of triangles. This enables to reduce the rendering time by reduction data size and by avoiding of redundant lighting and transformations computations. In this paper we present a new stripification algorithm for static fully triangulated meshes. Our new algorithm is based on the dual graph of triangulation. The experimental results show that our stripification produces much lower number of triangle strips than other stripification algorithms (except one)

关键词： Strips computer graphics Data visualization Rendering (computer graphics) Costs computer science Data engineering Solid modeling Application software computer aided manufacturing

来源：评论

学校读者我要写书评

暂无评论

Using gameplay semantics to procedurally generate player-matching game worlds 12

Using gameplay semantics to procedurally generate player-mat...

引用

Proceedings of the The third workshop on Procedural Content Generation in Games

作者： Ricardo Lopes Tim Tutenel Rafael Bidarra Computer Graphics and Visualization Group Delft University of Technology Mekelweg 4 2628 CD Delft The Netherlands

ISBN: (纸本)9781450314473

The use of procedural content generation to support adaptive games is starting to gain momentum in current research. However, there are still many open issues to tackle, namely the reusability of methodologies. Our research focuses on reusable and generic methods for linking the procedural generation of 3D game worlds with gameplay, as measured by player modelling techniques. As the interface for that link, we propose the use of gameplay semantics, a knowledge representation technique that allows our case-based generator to match content to player models. We present and discuss the implementation of our proposed method in an existing game, Stunt Playground. Gameplay semantics is created by designers in a generic way and is then used to procedurally generate player-matching Stunt Playground game worlds, both at the design and game stage. Current results show that our approach can automatically create such adaptive game content, thus effectively bridging game world designers, procedural generation and gameplay.

关键词： semantics adaptive game worlds procedural content generation

来源：评论

学校读者我要写书评

暂无评论

CFD simulation of liquid-liquid extraction columns and visualization of eulerian datasets

CFD simulation of liquid-liquid extraction columns and visua...

引用

International Research and Training Group 1131 Workshop on visualization of Large and Unstructured Data Sets: Applications in Geospatial Planning, Modeling and Engineering, VLUDS 2011

作者： Hlawitschka, Mark W. Chen, Fang Bart, Hans-Jörg Hamann, Bernd Department of Separation Science and Technology University of Kaiserslautern Germany Computer Graphics and HCI Group University of Kaiserslautern Germany CS Department Institute for Data Analysis and Visualization University of California Davis United States 2 University of Kaiserslautern Germany

ISBN: (纸本)9783939897460

In this joint work, a complete framework for modeling, simulating and visualizing multiphase fluid flow within an extraction column is presented. We first present a volume-of-fluid simulation, which is able to predict the surface of the droplets during coalescence. However, a fast and efficient model is needed for the simulation of a liquid-liquid extraction column due to the high number of occurring droplets. To simulate the velocity and droplet size in a DN32 extraction column, a coupled computational fluid dynamic-population balance model solver is used. The simulation is analyzed using path-line based visualization techniques. A novel semi-automatic re-seeding technique for droplet path-line integration is proposed. With our technique, path-lines of fluid droplets can be re-initialized after contact with the stirring devices. The droplet breakage is captured, allowing the engineer to improve the design of liquid-liquid columns layout.

关键词： Computational fluid dynamics

来源：评论

学校读者我要写书评

暂无评论

Feature Emphasis and Contextual Cutaways for Multimodal Medical visualization

Feature Emphasis and Contextual Cutaways for Multimodal Medi...

引用

9th Joint Eurographics/IEEE VGTC Symposium on visualization, EuroVis 2007

作者： Burns, Michael Haidacher, Martin Wein, Wolfgang Viola, Ivan Gröller, M. Eduard Imaging and Visualization Department Siemens Corporate Research PrincetonNJ United States Computer Science Department Princeton University United States Institute of Computer Graphics and Algorithms Vienna University of Technology Austria Department of Informatics University of Bergen Norway

ISBN: (纸本)9783905673456

Dense clinical data like 3D Computed Tomography (CT) scans can be visualized together with real-time imaging for a number of medical intervention applications. However, it is difficult to provide a fused visualization that allows sufficient spatial perception of the anatomy of interest, as derived from the rich pre-operative scan, while not occluding the real-time image displayed embedded within the volume. We propose an importance-driven approach that presents the embedded data such that it is clearly visible along with its spatial relation to the surrounding volumetric material. To support this, we present and integrate novel techniques for importance specification, feature emphasis, and contextual cutaway generation. We show results in a clinical context where a pre-operative CT scan is visualized alongside a tracked ultrasound image, such that the important vasculature is depicted between the viewpoint and the ultrasound image, while a more opaque representation of the anatomy is exposed in the surrounding area. © The Eurographics Association 2007.

关键词： visualization

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：