检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Mody, Prerak Chaves-De-Plaza, Nicolas F. Rao, Chinmay Astrenidou, Eleftheria de Ridder, Mischa Hoekstra, Nienke Hildebrandt, Klaus Staring, Marius Department of Radiology Leiden University Medical Center Leiden Netherlands HollandPTC consortium Erasmus Medical Center Rotterdam Holland Proton Therapy Centre Delft Leiden University Medical Center Leiden and TU Delft Delft Netherlands Computer Graphics and Visualization Group EEMCS TU Delft Delft Netherlands Department of Radiation Oncology Leiden University Medical Center Leiden Netherlands Department of Radiation Oncology University Medical Center Utrecht Netherlands

Increased usage of automated tools like deep learning in medical image segmentation has alleviated the bottleneck of manual contouring. This has shifted manual labour to quality assessment (QA) of automated contours which involves detecting errors and correcting them. A potential solution to semi-automated QA is to use deep Bayesian uncertainty to recommend potentially erroneous regions, thus reducing time spent on error detection. Previous work has investigated the correspondence between uncertainty and error, however, no work has been done on improving the "utility" of Bayesian uncertainty maps such that it is only present in inaccurate regions and not in the accurate ones. Our work trains the FlipOut model with the Accuracy-vs-Uncertainty (AvU) loss which promotes uncertainty to be present only in inaccurate regions. We apply this method on datasets of two radiotherapy body sites, c.f. head-and-neck CT and prostate MR scans. Uncertainty heatmaps (i.e. predictive entropy) are evaluated against voxel inaccuracies using Receiver Operating Characteristic (ROC) and Precision-Recall (PR) curves. Numerical results show that when compared to the Bayesian baseline the proposed method successfully suppresses uncertainty for accurate voxels, with similar presence of uncertainty for inaccurate voxels. Code to reproduce experiments is available at https://***/prerakmody/bayesuncertainty-error-correspondence. © 2024, CC BY.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Interactive focus+context rendering for hexahedral mesh inspection

arXiv

引用

arXiv 2020年

作者： Neuhauser, Christoph Wang, Junpeng Westermann, Rüdiger Computer Graphics & Visualization Group Technische Universität München Garching Germany

The visual inspection of a hexahedral mesh with respect to element quality is difficult due to clutter and occlusions that are produced when rendering all element faces or their edges simultaneously. Current approaches overcome this problem by using focus on specific elements that are then rendered opaque, and carving away all elements occluding their view. In this work, we make use of advanced GPU shader functionality to generate a focus+context rendering that highlights the elements in a selected region and simultaneously conveys the global mesh structure in the surrounding. To achieve this, we propose a gradual transition from edge-based focus rendering to volumetric context rendering, by combining fragment shader-based edge and face rendering with per-pixel fragment lists. A fragment shader smoothly transitions between wireframe and face-based rendering, including focus-dependent rendering style and depth-dependent edge thickness and halos, and per-pixel fragment lists are used to blend fragments in correct visibility order. To maintain the global mesh structure in the context regions, we propose a new method to construct a sheet-based level-of-detail hierarchy and smoothly blend it with volumetric information. The user guides the exploration process by moving a lens-like hotspot. Since all operations are performed on the GPU, interactive frame rates are achieved even for large meshes. Copyright © 2020, The Authors. All rights reserved.

关键词： Program processors

来源：评论

学校读者我要写书评

暂无评论

Development of distributed multimedia virtual environment with multichannel visualization of multimedia data by graphic accelerators 23

Development of distributed multimedia virtual environment wi...

引用

23rd International Conference on computer graphics and Vision, GraphiCon 2013

作者： Morozov, Boris B. Dolgovesov, Boris S. Mazurok, Boris S. Gorodilov, Mikhail A. Software Systems for Computer Graphics Laboratory Institute of Automation and Electrometry SB RAS Russia Synthesizing Visualization Systems Laboratory Institute of Automation and Electrometry SB RAS Russia Institute of Automation and Electrometry SB RAS Russia

ISBN: (纸本)9785804414024

An approach to the development of technical solutions for the creating of a real-time Distributed Multimedia Virtual Environment is described. The main objective of the environment - control the formation and delivery of multimedia content from multiple sources to multiple recipients. © 23rd International Conference on computer graphics and Vision, GraphiCon 2013 - Conference Proceedings. All rights reserved.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

The 3D Trajectory-based Stress Visualizer

arXiv

引用

arXiv 2021年

作者： Wang, Junpeng Neuhauser, Christoph Wu, Jun Gao, Xifeng Westermann, Rüdiger The Computer Graphics & Visualization Group Technische Universität München Garching Germany The Department of Sustainable Design Engineering Delft University of Technology Delft Netherlands The Lightspeed & Quantum Studio Tencent America United States

We present the 3D Trajectory-based Stress Visualizer (3D-TSV), a visual analysis tool for the exploration of the principal stress directions in 3D solids under load. 3D-TSV provides a modular and generic implementation of key algorithms required for a trajectory-based visual analysis of principal stress directions, including the automatic seeding of space-filling stress lines, their extraction using numerical schemes, their mapping to an effective renderable representation, and rendering options to convey structures with special mechanical properties. In the design of 3D-TSV, several perceptual challenges have been addressed when simultaneously visualizing three mutually orthogonal stress directions via lines. We present a novel algorithm for generating a space-filling and evenly spaced set of mutually orthogonal lines. The algorithm further considers the locations of lines to obtain a more regular pattern repetition, and enables the extraction of a Focus+Context representation with user-selected levels of detail for individual stress directions. To further reduce visual clutter, the system provides the combined visualization of two selected principal directions via appropriately oriented ribbons. The rendering uses depth cues to better convey the spatial relationships between trajectories and improves ribbon rendering on steep angles. 3D-TSV is accessible to end users via a C++- and OpenGL-based rendering frontend that is seamlessly connected to a MATLAB-based extraction backend. A TCP/IP-based communication interface supports the flexible integration of alternative rendering frontends. The code (BSD license) of 3D-TSV is made publicly available. Copyright © 2021, The Authors. All rights reserved.

关键词： Stresses

来源：评论

学校读者我要写书评

暂无评论

Learning a perceptual quality metric for correlation in scatterplots

Learning a perceptual quality metric for correlation in scat...

引用

2019 Conference on Vision, Modeling and visualization, VMV 2019

作者： Wöhler, L. Zou, Y. Mühlhausen, M. Albuquerque, G. Magnor, M. Computer Graphics Lab TU Braunschweig Germany Software for Space Systems and Interactive Visualization DLR Braunschweig Germany

ISBN: (纸本)9783038680987

Visual quality metrics describe the quality and efficiency of multidimensional data visualizations in order to guide data analysts during exploration tasks. Current metrics are usually based on empirical algorithms which do not accurately represent human perception and therefore often differ from the analysts’ expectations. We propose a new perception-based quality metric using deep learning that rates the correlation of data dimensions visualized by scatterplots. First, we created a data set containing over 15, 000 pairs of scatterplots with human annotations on the perceived correlation between the data dimensions. Afterwards, we trained two different Convolutional Neural Networks (CNN), one extracts features from scatterplot images and the other directly from data vectors. We evaluated both CNNs on our test set and compared them to previous visual quality metrics. The experiments show that our new metric is able to represent human perception more accurately than previous methods. © 2019 The Author(s) Eurographics Proceedings © 2019 The Eurographics Association.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Foreword to the special section on 3D object retrieval 2024 symposium (3DOR2024)

引用

computers and graphics 2025年 129卷

作者： Bustos, Benjamin Biasotti, Silvia Veltkamp, Remco C. Schreck, Tobias Sipiran, Ivan Department of Computer Science University of Chile Chile Chile Istituto di Matematica Applicata e Tecnologie Informatiche "E. Magenes" - CNR Italy Department of Information and Computing Sciences Utrecht University Netherlands Institute of Computer Graphics and Visualization Technical University of Graz Austria

来源：评论

学校读者我要写书评

暂无评论

PREVIS - A Combined Machine Learning and Visual Interpolation Approach for Interactive Reverse Engineering in Assembly Quality Control

引用

Procedia CIRP 2022年 112卷 483-488页

作者： Patrick Ruediger Felix Claus Viktor Leonhardt Hans Hagen Jan C. Aurich Christoph Garth Institute for Manufacturing Technolgy and Production Systems (FBK) Technische Universität Kaiserslautern P. O. Box 3049 67653 Kaiserslautern Germany Computer Graphics & HCI Lab Technische Universität Kaiserslautern P. O. Box 3049 67653 Kaiserslautern Germany Scientific Visualization Lab Technische Universität Kaiserslautern P. O. Box 3049 67653 Kaiserslautern Germany

We present PREVIS, a visual analytics tool, enhancing machine learning performance analysis in engineering applications. The presented toolchain allows for a direct comparison of regression models. In addition, we provide a methodology to visualize the impact of regression errors on the underlying field of interest in the original domain, the part geometry, via exploiting standard interpolation methods. Further, we allow a real-time preview of user-driven parameter changes in the displacement field via visual interpolation. This allows for fast and accountable online change management. We demonstrate the effectiveness with an ex-ante optimization of an automotive engine hood.

关键词： Explainable Machine Learning Quality Control Reverse Engineering Assembly Process visualization

来源：评论

学校读者我要写书评

暂无评论

Lossless compression of multi-view cultural heritage image data

Lossless compression of multi-view cultural heritage image d...

引用

2019 Eurographics Workshop on graphics and Cultural Heritage, GCH 2019

作者： Buelow, Max Von Guthe, Stefan Ritz, Martin Santos, Pedro Fellner, Dieter W. TU Darmstadt Germany Fraunhofer IGD Germany Graz University of Technology Institute of Computer Graphics and Knowledge Visualization Austria

ISBN: (纸本)9783038680826

Photometric multi-view 3D geometry reconstruction and material capture are important techniques for cultural heritage digitalization. Capturing images of artifacts with high resolution and high dynamic range and the possibility to store them losslessly enables future proof application of this data. As the images tend to consume immense amounts of storage, compression is essential for long time archiving. In this paper, we present a lossless image compression approach for multi-view and material reconstruction datasets with a strong focus on data created from cultural heritage digitalization. Our approach achieves compression rates of 2:1 compared against an uncompressed representation and 1.24:1 when compared against Gzip. © 2019 Eurographics Association.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

PREVIS-A combined machine learning and visual interpolation approach for interactive reverse engineering in assembly quality control

arXiv

引用

arXiv 2022年

作者： Ruediger, Patrick Claus, Felix Leonhardt, Viktor Hagen, Hans Aurich, Jan C. Garth, Christoph Technische Universität Kaiserslautern P. O. Box 3049 Kaiserslautern67653 Germany Computer Graphics & HCI Lab Technische Universität Kaiserslautern P. O. Box 3049 Kaiserslautern67653 Germany Scientific Visualization Lab Technische Universität Kaiserslautern P. O. Box 3049 Kaiserslautern67653 Germany

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

Visual Analysis of Tissue Images at Cellular Level

Visual Analysis of Tissue Images at Cellular Level

引用

23rd Eurographics Conference on visualization, EuroVis 2021

作者： Somarakis, A. Ijsselsteijn, Marieke E. Kenkhuis, Boyd van Unen, Vincent Luk, Sietse J. Koning, Frits van der Weerd, Louise de Miranda, Noel F.C.C. Lelieveldt, Boudewijn P.F. Höllt, T. Radiology Department Leiden University Medical Center Leiden Netherlands Pathology Department Leiden University Medical Center Leiden Netherlands Human Genetics Department Leiden University Medical Center Leiden Netherlands School of Medicine Stanford University StanfordCA United States Hematology Department Leiden University Medical Center Leiden Netherlands Immunology Department Leiden University Medical Center Leiden Netherlands Computer Graphics and Visualization Department TU Delft Delft Netherlands

ISBN: (纸本)9783038681472

The detailed analysis of tissue composition is crucial for the understanding of tissue functionality. For example, the location of immune cells related to a tumour area is highly correlated with the effectiveness of immunotherapy. Therefore, experts are interested in presence of cells with specific characteristics as well as the spatial patterns they form. Recent advances in single-cell imaging modalities, producing high-dimensional, high-resolution images enable the analysis of both of these features. However, extracting useful insight on tissue functionality from these high-dimensional images poses serious and diverse challenges to data analysis. We have developed an interactive, data-driven pipeline covering the main analysis challenges experts face, from the pre-processing of images via the exploration of tissue samples to the comparison of cohorts of samples. All parts of our pipeline have been developed in close collaboration with domain experts and are already a vital part in their daily analysis routine. © 2021 The Author(s) Eurographics Proceedings © 2021 The Eurographics Association.

关键词： Pipelines

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：