草绘3维人体建模的模板形变方法

目的 采用草绘交互方式直接构造3维人体模型是当前人体建模研究的重要课题之一.提出一种草绘3维人体建模的模板形变方法.方法 针对输入的草图,首先,采用关节点定位方法获取草图中的人体关节点,根据人体结构学约束识别人体骨架结构,通过解析人体轮廓草图获取人体草图特征;其次,通过骨架模板和外观轮廓模板形变,将草图特征映射到3维人体模型,实现3维人体建模.结果 草图解析方法能有效提取草图特征,通过模板形变方法生成3维人体模型,并在模型上保持草图特征;能适应不同用户的绘制习惯,且生成的3维人体模型可用于人体动画设计.结论 提出一种草绘3维人体建模的模板形变方法,支持用户采用草绘方式进行3维人体模型设计,方法具有良好的用户适应性,对3维动画创作具有重要意义.     

采用草绘轮廓的3维人脸建模方法

为方便用户进行3维人脸形状设计,提出一种基于手绘轮廓的3维人脸建模方法。该方法的主要特点在于,一方面,引用姿态估计技术对人脸草图进行解析,将用户绘制的侧视人脸草图转换成对应的正视人脸草图,可支持用户选择多个视角绘制人脸;另一方面,采用多层映射机制建立人脸草图特征点与3维人脸特征点之间的一一对应关系,由对应特征点之间的形变量来控制生成3维人脸,保证草图笔画的几何形状信息能有效映射到3维模型中。实验结果表明,文中方法能快速生成形状新颖的特定人脸,可有效支持用户进行3维人脸形状的手绘建模。     

草图交互式地质建模研究

提出一种简单、快捷的草图交互式地质建模方法,旨在帮助地质学家们在地质勘测初期直观、快速地创建无数据地质概念模型.迄今,现存专业地质建模工具依赖成本较高的真实数据创建精细复杂的三维地质模型,且通常具有建模用时长、不易于学习和使用等缺陷.因此,采用直观的“纸-笔”建模隐喻,提供了一套从草图绘制到三维模型创建,再到三维模型编辑的完整建模流程,允许用户在自由定义的绘图平面上绘制描述模型地质特征的三维草图,并对其构成的连通草图网络实时地进行三维模型重建.模型重建使用分治的思想,大致分为3个步骤完成：首先利用三维草图的几何信息,即拐点,根据其拓扑连接搜寻草图网络中近似平面的能量最小圈,然后通过调和函数计算草图网络中每个圈包围区域的目标平均曲率标量及其法线方向,随后以Laplacian方程优化生成曲面片,最后将曲面片拼接成完整的三维模型.褶皱、断层地质现象可以分别通过重绘和切割操作进行建模.此外,利用层级结构树存储地质模型间的层级关系,并通过变形传递的方式对与形变物体接触的地质模型进行形变,从而保持了地质结构中多物质体相互接触的特性.相比现有基于草图的交互式建模工具,该方法融合了地质学知识,且能够更有效地使用少量草图描述地质物体的特征.基于用户体验调查,该方法具有操作简单、建模直观的特点,能够同时满足专业和非专业人士快速创建地质概念模型的需求.     

一种基于手绘草图的三维建模方法研究

研究一种基于手绘草图进行三维建模的方法。将用户界面分为手势区、轮廓区、控制区、信息提示区等。根据手势区输入的手势以及控制区输入的控制信息,对轮廓区输入的二维信息构建三维模型。采用模板匹配的方法识别用户手势,采用容差环的方法识别用户输入的物体轮廓,根据生成的三维数据之间的分层信息构建物体表面三角网格,对物体进行三维建模。     

虚拟植物叶片的可视化建模技术研究

植物叶片的真实感建模技术一直是虚拟植物仿真技术的研究热点和难点。从植物叶片的形态结构和纹理特征出发,提出一种基于图像的树叶仿真方法。通过对一幅树叶图像进行边缘检测并配合Marching Square算法,实现对树叶复杂轮廓信息的准确提取;利用Delaunay三角剖分的优化算法对叶片进行三角形网格化处理,得到具有均匀三角形网格的叶片模型;最后以叶脉作为变形控制骨架,采用基于Laplace方程的迭代变形算法完成二维叶片向三维变形叶片的重建,以模拟叶片表面的自然弯曲变形效果,增强叶片模型的真实感。相比于以往的树叶建模仿真方法,突出了叶脉在网格划分及树叶形变中所起的作用,所建模型能更逼真地反映真实植物叶片的形态特征,提高了叶片的真实感仿真程度。     

一种基于视图分类的3维模型检索方法

3维模型检索是近年来基于内容检索的研究热点。在基于2维草图检索3维模型的研究中,通常没有结合人的知识。为了提高3维模型检索的精度,提出了一种基于视图分类的3维模型检索方法,它的主要思想是通过视图分类将人对3维模型的认知变换为对2维视图的理解,以便在度量2维草图与视图之间的相似性时能利用人的知识。该方法涉及以下2个问题:视图分类、2维草图与视图之间的相似性度量。实验结果表明,该方法能提高检索精度,因此可应用在2维草图查询方式的3维模型检索中。     

在线手绘草图识别中的用户建模方法

提出了一种在线手绘草图识别的用户建模方法。该方法首先利用用户输入笔划的速率和曲率特性进行笔划特征点抽取和笔划分段,从而将用户的输入草图分解成基本图元表示;进而,利用决策树收集和记录用户输入草图的时序信息,实现对复杂手绘草图的用户建模和在线识别,并通过对用户输入模式使用频率的统计实现对用户模型的动态管理和更新。实验表明:该方法不仅能显著提高复杂图形的识别效率,而且具有在线训练能力。     

基于手绘草图的视觉内容生成深度学习方法综述

手绘草图通过绘制简单的线条直观呈现用户的创作意图, 支持用户采用手绘的方式快速表达思维过程及设计灵感, 创作目标图像或视频. 随着深度学习的发展, 基于草图的视觉内容生成通过学习草图和视觉对象(即图像和视频)的特征分布进行跨领域特征映射, 实现图像自动生成草图以及草图自动生成对应的图像或视频, 与传统的人工创作方式相比有效地提高了生成的效率和多样性, 成为计算机视觉、图形学领域的重要研究方向, 并且在设计、视觉创作等领域具有重要作用. 综述基于草图的视觉内容生成深度学习方法的研究现状和发展趋势, 按照视觉对象的不同将现有工作分为基于草图的图像生成和基于草图的视频生成方法, 并结合草图和视觉内容跨域生成、风格转化、视觉内容编辑等任务对生成模型进行详细分析, 然后比较和总结常用的数据集、针对草图数据不足提出的扩充方法以及生成模型的评估方法, 进一步通过草图在视觉内容生成应用中面临的挑战及生成模型未来发展方向对研究趋势进行展望.     

基于草图界面的设计方案复用研究

当前的CAD工具缺乏对构思活动中各种设计知识的有效建模,造成设计方案难以在后续工作中灵活、快速地复用.采用基于草图界面的自然交互方式,通过对设计过程中草图信息的分析与建模实现对设计过程的描述;在复用过程中向用户提供推荐方案,支持设计意图的自然表达和方案的灵活复用,从而降低用户认知负担.实验结果表明,这种基于草图信息分析与建模的设计方案能满足敏捷设计的需要,实现了设计方案的灵活复用.     

在线草图识别中用户手绘习惯建模方法

手绘草图是概念设计和思路外化的一种高效的表达方式。用户绘制草图时存在的多种形式，及其随意性和模糊性使得用户适应性问题逐渐成为草图识别的核心课题。本文提出了一种在线草图识别的用户建模方法来捕捉绘制草图时的用户习惯，主要包括两个方面的内容：一是基于SVM的主动式增量学习方法，二是基于动态用户建模的手绘复杂图形的识别方法。前者与传统的增量式学习方法相比，在识别精度相同的情况下所需的训练时间和训练数据集要少得多。后者则是基于笔划信息以及笔划间的顺序和空间关系信息，采用增量式决策树捕捉用户的输入习惯和过程信息。实验证明了本文方法在在线草图识别中的有效性和高效性。     

Analysing students' shared activity while modeling a biological process in a computer-supported educational environment

Abstract  This paper reports on a case study with three dyads of high school students (age 14 years) each collaborating on a plant growth modeling task in the computer-supported educational environment ' ModelsCreator '. Following a qualitative line of research, the present study aims at highlighting the ways in which the collaborating students as well as the facilitator who supported them are engaged in the computer-based modeling 'activity'. The analysis is carried out with a two-level analytic tool that has been derived within the theoretical framework of 'activity theory'. Our results show that a wide range of modeling 'operations' is activated in the context of the three major modeling 'actions' of 'analysis', 'synthesis' and 'testing-interpreting', which take place in the light of the facilitator-driven 'action' of cognitive and technical support. Moreover, these actions are combined into 'modeling units' of various forms which are repeated several times until the modeling process comes to an end. These many-fold repeats of the 'modeling unit' appear to shape a pattern which characterizes the computer-supported shared 'activity' as a whole.     

Context-aware garment modeling from sketches

Modeling of realistic garments is essential for creating believable virtual environments. Sketch-based modeling of garments presents an appealing, easy to use alternative to the established modeling approaches which are time consuming and require significant tailoring expertise. Unfortunately, the results created using existing sketch-based methods lack realism. Driven by human perception of garment sketches, we propose a context-aware garment sketch interpretation based on a set of observations about key factors that affect the shape of garments. Based on this analysis we develop a geometric method for sketch-based modeling of garments which obtains more realistic results than previous techniques. We demonstrate the effectiveness of our method on a variety of inputs and validate our approach via a user study where viewers were asked to compare the believability of our outputs versus previous ones.     

A ‘context-aware’ and agent-centric perspective for the alignment between individuals and organizations

The enterprise modeling field aims at representing organizations from several, inter-related perspectives. A number of enterprise modeling frameworks have been developed providing models, methods and tools that enable to communicate the structure and processes of organizations. These frameworks have been used both for systems development and organizational analysis ends, where the latter mainly focuses process (re)design efforts. We argue that enterprise modeling frameworks can be used for other kinds of organizational analysis. In particular, they can be used to capture and model work practices, human multitasking at work, and to compare models describing pre-defined behavior with actual execution.     

三维CAD 混合建模技术研究

三维数字化建模主要有两种技术：一是参数化建模,二是直接建模。但这 两种技术在实际应用中均存在缺陷。论文将两种建模方法融合在一起形成混合建模技术,能 更好地体现设计者的意图,提高设计效率。     

三维地质模型分析概述

由于三维地质建模需要对矿体的品位等属性信息进行详细的描述,所以三维地学建模须采用基于体元的方法建模,也可以由表面模型栅格化为体元模型。综述了现在常用的三维地质建模的一般方法,实体模型、四面体、块体模型、结构实体几何、似三棱柱等,并对各自的优缺点进行了分析,着重介绍了基于体元的建模方法,可为三维地质建模初学者提供一定的参考。     

A procedure for building product models

The application of product modeling in manufacturing companies raises the important question of how to model product knowledge in a comprehensible and efficient way. An important challenge is to qualify engineers to model and specify IT-systems (product models) to support their specification activities. A basic assumption is that engineers have to take the responsibility for building product models to be used in their domain. To do that they must be able to carry out the modeling task on their own without any need for support from computer science experts. This paper presents a set of simple, easily adaptable concepts and methods for modeling product knowledge. The concepts and methods are based on well-defined concepts and methods from data modeling (object oriented analysis) and domain modeling (product modeling). The concepts are general and can be used for modeling all types of specifications in the different phases in the product life cycle. The modeling techniques presented have been tested in different companies and have proved to work.     

MuscleBuilder: A modeling tool for human anatomy

A traditional multi-layered approach is adopted to human body modeling and deformation. The model is split into three general anatomical structures: the skeleton, musculature and skin. It is shown that each of these layers is modeled and deformed by using fast, procedural, ad-hoc methods that can painlessly be reimplemented. The modeling approach is generic enough to handle muscles of varying shape, size and characteristics and does not break in extreme skeleton poses. It is also described that the integrated MuscleBuilder system whose main features are: i) easy and quick creation of muscle deformation models; ii) automatic deformation of an overlying skin. It is shown that visually realistic results can be obtained at interactive frame rates with very little input from the designer.     

A Curvature and Density‐based Generative Representation of Shapes

This paper introduces a generative model for 3D surfaces based on a representation of shapes with mean curvature and metric, which are invariant under rigid transformation. Hence, compared with existing 3D machine learning frameworks, our model substantially reduces the influence of translation and rotation. In addition, the local structure of shapes will be more precisely captured, since the curvature is explicitly encoded in our model. Specifically, every surface is first conformally mapped to a canonical domain, such as a unit disk or a unit sphere. Then, it is represented by two functions: the mean curvature half‐density and the vertex density, over this canonical domain. Assuming that input shapes follow a certain distribution in a latent space, we use the variational autoencoder to learn the latent space representation. After the learning, we can generate variations of shapes by randomly sampling the distribution in the latent space. Surfaces with triangular meshes can be reconstructed from the generated data by applying isotropic remeshing and spin transformation, which is given by Dirac equation. We demonstrate the effectiveness of our model on datasets of man‐made and biological shapes and compare the results with other methods.     

Location-based services and GIS in perspective

This paper examines location-based services (LBS) from a broad perspective involving definitions, characteristics, and application prospects. We present an overview of LBS modeling regarding users, locations, contexts and data. The LBS modeling endeavors are cross-examined with a research agenda of geographic information science. Some core research themes are briefly speculated.     

SOA全生命周期建模方法综述

在介绍SOA(面向服务的架构)项目实施过程的基础上,从SOA全生命周期的视角,着重从方法论上对实施SOA项目所涉及到的业务流程建模、服务建模、数据建模、服务集成建模和业务监控建模进行了分析与评述,并提供了一些新的解决思路,同时指出了SOA建模领域的一些研究热点及趋势。