检索结果-内蒙古大学图书馆

GeoCode: Interpretable Shape Programs

computer graphics FORUM 2025年第1期44卷

作者： Pearl, Ofek Lang, Itai Hu, Yuhua Yeh, Raymond A. Hanocka, Rana Tel Aviv Univ Sch Elect Engn Tel Aviv Israel Univ Chicago Dept Comp Sci Chicago IL 60611 USA Purdue Univ Dept Comp Sci W Lafayette IN USA

The task of crafting procedural programs capable of generating structurally valid 3D shapes easily and intuitively remains an elusive goal in computer vision and graphics. Within the graphics community, generating procedural 3D models has shifted to using node graph systems. They allow the artist to create complex shapes and animations through visual programming. Being a high-level design tool, they made procedural 3D modelling more accessible. However, crafting those node graphs demands expertise and training. We present GeoCode, a novel framework designed to extend an existing node graph system and significantly lower the bar for the creation of new procedural 3D shape programs. Our approach meticulously balances expressiveness and generalization for part-based shapes. We propose a curated set of new geometric building blocks that are expressive and reusable across domains. We showcase three innovative and expressive programs developed through our technique and geometric building blocks. Our programs enforce intricate rules, empowering users to execute intuitive high-level parameter edits that seamlessly propagate throughout the entire shape at a lower level while maintaining its validity. To evaluate the user-friendliness of our geometric building blocks among non-experts, we conduct a user study that demonstrates their ease of use and highlights their applicability across diverse domains. Empirical evidence shows the superior accuracy of GeoCode in inferring and recovering 3D shapes compared to an existing competitor. Furthermore, our method demonstrates superior expressiveness compared to alternatives that utilize coarse primitives. Notably, we illustrate the ability to execute controllable local and global shape manipulations. Our code, programs, datasets and Blender add-on are available at .

关键词： curves and surfaces image-based modelling modelling modelling interfaces

来源：评论

学校读者我要写书评

暂无评论

Genetic Subdivision Curve and Surface Reconstruction 32

Genetic Subdivision Curve and Surface Reconstruction

引用

32nd International Conference in Central Europe on computer graphics, Visualization and computer vision, WSCG 2024

作者： Komar, Alexander Riegler, Marco Preiner, Reinhold Augsdörfer, Ursula Institute of Computer Graphics and Knowledge Visualisation Graz University of Technology Austria

In this paper we employ a new genetic algorithm approach for CAD shape reconstruction, where a mathematical shape representation is reconstructed from point data. We reconstruct planar subdivision curves and 3D subdivision meshes from ordered input point data by fitting the corresponding subdivision control polygon or control mesh respectively, from which the smooth subdivision limit surfaces can be derived. For the reconstruction of curves the system estimates the number and position of control points required to approximate the curve closely. To reconstruct subdivision surfaces from points, the system determines a sequence of CAD operations which is subject to mutation in the course of a genetic optimization. We discuss implementation details of the proposed genetic algorithms and demonstrate our approach on a number of example data. © 2024 University of West Bohemia. All rights reserved.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

31st International Conference in Central Europe on computer graphics, Visualization and computer vision, WSCG 2023 - Proceedings

31st International Conference in Central Europe on Computer ...

引用

31st International Conference in Central Europe on computer graphics, Visualization and computer vision, WSCG 2023

ISBN: (纸本)9788086943329

The proceedings contain 49 papers. The topics discussed include: investigation on encoder-decoder networks for segmentation of very degraded x-ray CT tomograms;self-checkout product class verification using center loss approach;why existing multimodal crowd counting datasets can lead to unfulfilled expectations in real-world applications;perceptions of color pickers in virtual reality art-making;modeling and rendering with expressive B-Spline curves;sail: semantic analysis of information in light fields: results from synthetic and real-world data;texture spectral similarity criteria comparison;designing a lightweight edge-guided convolutional neural network for segmenting mirrors and reflective surfaces;synthetic-real domain adaptation for probabilistic pose estimation;error-robust indoor augmented reality navigation: evaluation criteria and a new approach;and visualization of deviations between different geometries using a multi-level voxel-based representation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Approximation of photovoltaic characteristics curves using Bezier Curve

引用

RENEWABLE ENERGY 2021年 174卷 715-732页

作者： Louzazni, Mohamed Al-Dahidi, Sameer Chouaib Doukkali Univ Natl Sch Appl Sci Lab Energy El Jadida Morocco German Jordanian Univ Sch Appl Tech Sci Dept Mech & Maintenance Engn Amman 11180 Jordan

Accuracy of solar cell model parameters is now a requirement for the manufacturing of appropriate photovoltaic models. Consequently, the methodologies of the parameters had already attracted immense interest among researchers over the years. This paper deals about the approximation of the characteristics curves of a solar cell using the Bezier curve method. This technique is selected to overcome the problems of the non-linearity, complexity, multivariate and multimodal of the characteristic's curves. The Bezier curves method is a parametric curve used throughout computer graphics and related disciplines. It is a robust methodology for constructing free-form curves, surfaces, shape design, and geometric representation of various products. Six different cases are carried out to test the validity of the proposed method, they are: (i) organic flexible dual junction amorphous silicon solar cell, (ii) silicon solar cell, (iii) Schutten Solar STP6-120/36 polycrystalline photovoltaic module, (iv) Schutten Solar STM6-40/36 monocrystalline photovoltaic module, (v) Photowatt-PWP 201 polycrystalline photovoltaic module and (vi) 230-W multi-silicon photovoltaic module under partial shading conditions. The technique is implemented and adapted by the mean of the De Casteljo algorithm to optimize the control points and minimize the distance between the experimental and calculated points. It is based on subdividing the curve into various segments and controlled by control points using the De Casteljo algorithm to minimize the distance between the experimental and theoretical points. The performance of the approximated characteristics curves is compared with experimental data as well as recent algorithms and techniques from the literature. For more validity, statistical error metrics from literature are computed and compared to ensure the accuracy of the approximated results and the performance of the proposed method. For instance, the comparison is carried out by resorting to the In

关键词： Approximation Photovoltaic Bezier curves method Algorithms Theoretical points

来源：评论

学校读者我要写书评

暂无评论

ECHO: Extended Convolution Histogram of Orientations for Local Surface Description

引用

computer graphics FORUM 2021年第1期40卷 180-194页

作者： Mitchel, Thomas W. Rusinkiewicz, Szymon Chirikjian, Gregory S. Kazhdan, Michael Johns Hopkins Univ Baltimore MD 21218 USA Princeton Univ Princeton NJ 08544 USA Natl Univ Singapore Singapore Singapore

This paper presents a novel, highly distinctive and robust local surface feature descriptor. Our descriptor is predicated on a simple observation: instead of describing the points in the vicinity of a feature point relative to a reference frame at the feature point, all points in the region describe the feature point relative to their own frames. Isometry invariance is a byproduct of this construction. Our descriptor is derived relative to the extended convolution - a generalization of the standard convolution that allows the filter to adaptively transform as it passes over the domain. As such, we name our descriptor the Extended Convolution Histogram of Orientations (ECHO). It exhibits superior performance compared to popular surface descriptors in both feature matching and shape correspondence experiments. In particular, the ECHO descriptor is highly stable under near-isometric deformations and remains distinctive under significant levels of noise, tessellation, complex deformations and the kinds of interference commonly found in real data.

关键词： 3D shape matching modeling curves and surfaces modeling computer vision – shape recognition methods and applications

来源：评论

学校读者我要写书评

暂无评论

Toward Automatic Interpretation of 3D Plots 16th

Toward Automatic Interpretation of 3D Plots

引用

16th IAPR International Conference on Document Analysis and Recognition (ICDAR)

作者： Brandt, Laura E. Freeman, William T. MIT CSAIL Cambridge MA 02139 USA NSF AI Inst Artificial Intelligence & Fundamental Cambridge MA USA

ISBN: (纸本)9783030863319

This paper explores the challenge of teaching a machine how to reverse-engineer the grid-marked surfaces used to represent data in 3D surface plots of two-variable functions. These are common in scientific and economic publications;and humans can often interpret them with ease, quickly gleaning general shape and curvature information from the simple collection of curves. While machines have no such visual intuition, they do have the potential to accurately extract the more detailed quantitative data that guided the surface's construction. We approach this problem by synthesizing a new dataset of 3D grid-marked surfaces (SurfaceGrid) and training a deep neural net to estimate their shape. Our algorithm successfully recovers shape information from synthetic 3D surface plots that have had axes and shading information removed, been rendered with a variety of grid types, and viewed from a range of viewpoints.

关键词： 3D plot interpretation Figure analysis Data extraction Shape-from-x graphics recognition Neural network computer vision

来源：评论

学校读者我要写书评

暂无评论

Filling the Holes on 3D Heritage Object Surface based on Automatic Segmentation Algorithm

arXiv

引用

arXiv 2023年

作者： Van, Sinh Nguyen, B. Le, Son Thanh Tran, Minh Khai Sach, Le Thanh School of Computer Science and Engineering International University - VNUHCM Viet Nam School of Computer Science and Engineering Ho Chi Minh City University of Technology VNUHCM Viet Nam

Reconstructing and processing the 3D objects are popular activities in the research field of computer graphics, image processing and computer vision. The 3D objects are processed based on the methods like geometric modeling (a branch of applied mathematics and computational geometry) or the machine learning algorithms based on image processing. The computation of geometrical objects includes processing the curves and surfaces, subdivision, simplification, meshing, holes filling, reconstructing and refining the 3D surface’s objects on both point cloud data and triangular mesh. While the machine learning methods are developed using deep learning models. With the support of 3D laser scan devices and LiDAR techniques, the obtained dataset is close to original’s shape of the real objects. Besides, the photography and its application based on the modern techniques in recent years help us collect data and process the 3D models more precise. This article propose an improved method for filling holes on the 3D object’s surface based on an automatic segmentation. Instead of filling the hole directly as the existing methods, we now subdivide the hole before filling it. The hole is first determined and segmented automatically based on computation of its local curvature. It is then filled on each part of the hole to match its local curvature shape. The method can work on both 3D point cloud surfaces and triangular mesh surface. Comparing to the state-of-the-art (SOTA) methods, our proposed method obtained higher accuracy of the reconstructed 3D objects. Copyright © 2023, The Authors. All rights reserved.

关键词： Filling

来源：评论

学校读者我要写书评

暂无评论

图形图像积分与微分不变量的构造与应用

引用

图学学报 2022年第6期43卷 1182-1192页

作者：墨瀚林郝优郭锐郝宏翔张贺李琪李华中国科学院计算技术研究所智能信息处理重点实验室北京100190 中国科学院大学计算机科学与技术学院北京100049

作为图形图像数据的常用特征,微分不变量和以矩不变量为代表的积分不变量在计算机视觉、模式识别和计算机图形学等领域扮演了重要角色。在过去二十年中,本研究团队利用基本生成函数构造了灰度图像、彩色图像、向量场、点云、曲线和网格... 详细信息

作为图形图像数据的常用特征,微分不变量和以矩不变量为代表的积分不变量在计算机视觉、模式识别和计算机图形学等领域扮演了重要角色。在过去二十年中,本研究团队利用基本生成函数构造了灰度图像、彩色图像、向量场、点云、曲线和网格曲面等图形图像数据在几何变换、颜色变换、图像模糊和全变换下的矩不变量;证明了仿射变换下几何矩不变量与微分不变量之间满足同构关系,提出了一种获取仿射微分不变量的简单方法,并进一步得到了射影变换和莫比乌斯变换下图形图像的微分不变量;为了增强深度神经网络对常见图形图像变换的不变性,探索了如何将图形图像不变量引入深度神经网络模型。系统回顾与总结了上述工作,简要介绍了如何使用基本生成函数构造图形图像在仿射变换下的几何矩不变量与微分不变量,分析了图形图像不变量的典型应用场景及优缺点,并对未来的研究进行了展望。

关键词：图形图像变换特征提取矩不变量微分不变量图像分类形状分析模板匹配

来源：评论

学校读者我要写书评

暂无评论

The ZTF Source Classification Project: iii. A Catalog of Variable Sources

arXiv

引用

arXiv 2023年

作者： Healy, Brian F. Coughlin, Michael W. Mahabal, Ashish A. Laz, Theophile Jegou du Drake, Andrew Graham, Matthew J. Hillenbrand, Lynne A. van Roestel, Jan Szkody, Paula Zielske, LeighAnna Guiga, Mohammed Hassan, Muhammad Yusuf Hughes, Jill L. Nir, Guy Parikh, Saagar Park, Sungmin Purohit, Palak Rebbapragada, Umaa Reed, Draco Warshofsky, Daniel Wold, Avery Bloom, Joshua S. Masci, Frank J. Riddle, Reed Smith, Roger School of Physics and Astronomy University of Minnesota MinneapolisMN55455 United States Division of Physics Mathematics and Astronomy California Institute of Technology PasadenaCA91125 United States Center for Data Driven Discovery California Institute of Technology PasadenaCA91125 United States Department of Astronomy California Institute of Technology PasadenaCA91125 United States Anton Pannekoek Institute for Astronomy University of Amsterdam Amsterdam1090 GE Netherlands Department of Astronomy University of Washington SeattleWA98195 United States Department of Physics Pacific Lutheran University TacomaWA98447 United States Department of Computer Science and Engineering University of Minnesota MinneapolisMN55455 United States Department of Electrical Engineering Indian Institute of Technology Gandhinagar Gujarat 382055 India Department of Astronomy University of California BerkeleyCA94720 United States Lawrence Berkeley National Laboratory 1 Cyclotron Road MS 50B-4206 BerkeleyCA94720 United States Department of Electrical and Computer Engineering Carnegie Mellon University PittsburghPA15213 United States Computer Vision Imaging and Graphics Lab Indian Institute of Technology Gujarat Gandhinagar382055 India School of Statistics University of Minnesota MinneapolisMN55455 United States Division of Engineering and Applied Science California Institute of Technology PasadenaCA91125 United States Jet Propulsion Laboratory California Institute of Technology PasadenaCA91125 United States IPAC California Institute of Technology 1200 E. California Blvd. PasadenaCA91125 United States Caltech Optical Observatories California Institute of Technology PasadenaCA91125 United States

The classification of variable objects provides insight into a wide variety of astrophysics ranging from stellar interiors to galactic nuclei. The Zwicky Transient Facility (ZTF) provides time-series observations that record the variability of more than a billion sources. The scale of these data necessitates automated approaches to make a thorough analysis. Building on previous work, this paper reports the results of the ZTF Source Classification Project (SCoPe), which trains neural network and XGBoost machine-learning (ML) algorithms to perform dichotomous classification of variable ZTF sources using a manually constructed training set containing 170,632 light curves. We find that several classifiers achieve high precision and recall scores, suggesting the reliability of their predictions for 209,991,147 light curves across 77 ZTF fields. We also identify the most important features for XGB classification and compare the performance of the two ML algorithms, finding a pattern of higher precision among XGB classifiers. The resulting classification catalog is available to the public, and the software developed for SCoPe is open-source and adaptable to future time-domain surveys. Copyright © 2023, The Authors. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

A Variational Approach to Registration with Local Exponential Coordinates

引用

computer graphics FORUM 2019年第1期38卷 482-506页

作者： Paman, Ashish Rangarajan, Ramsharan Indian Inst Sci Bangalore Dept Mech Engn Bengaluru India

We identify a novel parameterization for the group of finite rotations (SO3), consisting of an atlas of exponential maps defined over local tangent planes, for the purpose of computing isometric transformations in registration problems that arise in machine vision applications. Together with a simple representation for translations, the resulting system of coordinates for rigid body motions is proper, free from singularities, is unrestricted in the magnitude of motions that can be represented and poses no difficulties in computer implementations despite their multi-chart nature. Crucially, such a parameterization helps to admit varied types of data sets, to adopt data-dependent error functionals for registration, seamlessly bridges correspondence and pose calculations, and inspires systematic variational procedures for computing optimal solutions. As a representative problem, we consider that of registering point clouds onto implicit surfaces without introducing any discretization of the latter. We derive coordinate-free stationarity conditions, compute consistent linearizations, provide algorithms to compute optimal solutions and examine their performance with detailed examples. The algorithm generalizes naturally to registering curves and surfaces onto implicit manifolds, is directly adaptable to handle the familiar problem of pairwise registration of point clouds and allows for incorporating scale factors during registration.

关键词： computer vision - tracking methods and applications implicit surfaces modelling computational geometry

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：