基于手绘的三维建模系统的研究和实现*

研究基于手绘(sketch)的三维建模方法并实现相应的建模系统。通过对输入的手绘笔画(strokes)进行去噪、分段、识别等操作,将手绘笔画识别为直线、椭圆等基本图元,再根据图元之间的相应关系构建出三维模型,实现对用户输入意图的自动三维解释。实验结果表明,该方法能够对输入的strokes进行精确的分析处理,实现对输入手绘笔画的三维建模。     

一种基于手绘的自由形体建模方法研究

提出了一种基于手绘的自由形体建模方法。通过平滑去噪、重采样、曲线拟合等操作,将输入的手绘笔画转化为均匀间隔的点序列,根据提取到的几何信息生成三维网格模型,并通过对模型进行光照渲染和纹理贴图完成具有特定形状的自由形体的绘制。实验结果表明,该方法能够简单快速地实现符合用户输入意图的三维形体建模。     

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。     

基于手绘花瓣的花朵建模方法

针对现有花朵建模方法形成的花瓣式样与形态单一的缺陷,提出一种基于手绘花瓣的交互式花朵建模方法。该方法首先根据手绘花瓣的轮廓图提取花瓣模型的二维控制点,然后通过弯曲控制函数得到花瓣的三维控制点,继而利用三维控制点构造三维花瓣模型,最后由经过真实感渲染的单个花瓣构建花朵。实验结果表明,与其他建模方法相比,该建模方法能够方便地生成各种裂瓣状花瓣的花朵且真实感更强。     

基于手绘输入理解的智能3D几何建模系统

近年来,图形学领域已经开发了大量的3D建模和可视化工具,但是这些工具的界面往往过于复杂,制约了设计人员的创造性工作,也进一步限制了这些工具为普遍用户所使用。事实上,理想的3D建模工具应该提供给用户以尽可能自然、简单的操作,例如基于电子笔的草图输入,而且随着移动设备的发展,也使之成为图形学中更有前景的研究方向。文章论述了当前支持手绘的建模技术的研究现状,并提出了一个更加智能化的多模块建模体系,突出了交互技术、智能理解和高质量的可视化输出技术的结合;而且针对手绘输入的不明确性,着重分析了图形数据的基于特性的语义描述,提出了智能的逻辑推理模型,并进一步描述了下一代融合自然输入、逻辑推理与虚拟显示于一体的智能图形建模系统的实现。预测了人工智能技术与CA D技术的结合将是未来图形学领域发展的主要方向之一。     

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。     

融合手绘风格的卡通角色动画生成方法

手绘风格的卡通动画具有灵活、自然、表现力强等特点.为了快速地创作体现手绘风格的卡通角色动画,提出一种基于多视点手绘图的动画生成方法.首先利用手绘图构建角色的三维网格和骨架子空间模型;然后结合姿态重建和微分域网格变形算法,创建一组与多视点手绘图相匹配的视点相关模型,以表达手绘风格;最后通过运动标注和启发式泛化算法将手绘风格融入输入的运动序列,使生成的动画既保留运动序列的原始特征,又体现手绘图的笔画风格.实验结果表明,该方法能够有效地生成体现手绘风格的卡通角色动画.     

基于手绘线条的三维模型雕刻

为了生成复杂模型表面的几何纹理,提出一种三维模型的高效雕刻方法.首先根据用户交互方式生成手绘线条,通过曲线细化操作确定手绘曲线经过的三维模型表面边点,并去除手绘曲线经过的模型三角面片,将去除部分经三角剖分成小三角面片之后再插入到原始模型中;然后计算三维模型上的顶点到手绘线条集的距离,确定三维模型上与手绘曲线集的距离小于等于特定纹理宽度的顶点,并根据用户选取的轮廓函数计算顶点平移距离以及平移方向;最后对三维模型上手绘线条附近的顶点进行平移,得到模型的雕刻效果.实验结果表明,该方法能够方便、高效地实现三维模型表面的线条雕刻效果.     

基于深度学习的人体动作草图到三维骨骼模型重建方法的研究

为了提高三维人体骨骼模型的建模效率并简化交互规则,提出了一种基于深度学习的手绘人体动作草图到三维骨骼模型的重建方法。首先将三维骨骼模型渲染为二维图像来建立维度映射关系,进而使用图像分类方法识别手绘草图动作并根据维度映射实现三维骨骼模型重建。在实验中使用基于深度卷积神经网络对图像分类模型进行构建,使用浅层卷积网络作为训练单元,并使用逐级分类与分块训练策略加速网络收敛速度来提高训练效率。最后实验结果验证了该方法的可行性与有效性。     

基于描绘单幅图像的三维树木交互建模系统

为了提高树木建模的真实感与可交互性,提出了一种基于单幅树木图像或直接手绘的交互式植物建模系统。系统根据植物形态学规律构建了标准三维树木的模板。通过描绘图像中树的主要枝干,结合叶序周规律,基于三维模板树将其从二维图像变换到三维模型,并通过弯曲、增加和删除枝干以及添加树叶等交互式操作生成和修改三维树木模型。实验结果表明,该系统能便捷快速地生成真实感较强的三维树木。     

Conceptual design, manufacturability evaluation and preliminary process planning using function-form relationships in stamped metal parts

A large number of design decisions are made during the conceptual design of a part. However, there are few representation and reasoning tools for decision support during conceptual design. The conceptual design stage is characterized by a lack of complete geometric information. Existing geometric modelers require complete geometric information, while a functional reasoning methodology using a <verb, noun > representation is typically too terse. In this paper, we present a new representation called sketching abstraction for conceptual design, using the function-form relations in a design. The functionally critical part of the geometry is presented using a set of functional features, while the rest of the geometry is abstracted as a set of linkages. Part functionality is correlated with the sketching abstraction using data structures called function-form matrices. The sketching abstraction is annotated using a set of primitives, and a set of grammar rules are used to extract canonical relationships between the functional features. The sketching abstraction can be used for extracting designs that are geometrically dissimilar but functionally similar, thus providing the designer with ideas for design alternatives. The sketching abstraction can also be used to carry out domain-dependent manufacturability evaluation checks. A further use of sketching abstractions is to initiate the development of a process plan for manufacturing. Sketching abstractions are related to the solid model of a part. Thus, this representation provides a link between pure functional and pure geometric representations. The domain of application is stamped metal parts. We present the part functionality and the features used in this domain. We also illustrate the use of sketching abstractions for conceptual design, manufacturability evaluation and preliminary process planning.     

试论动画素描教学的专业指向性

动画专业是培养动画艺术作品设计与制作专门人才的教学学科,具有较强的专业性。作为这一专业的基础课程,动画素描的教学必然在一定程度上相应地体现出与传统绘画素描和现代设计素描不同的、与动画专业特点相对应的明显的专业指向性。因而,如何构建与动画专业教学相适应的素描教学体系,从而使动画素描教学适应动画专业教学、真正为动画专业教学与动画创作奠定基础,是当前动画专业教学亟待解决的问题,是一个值得我们去探讨的课题。     

Electronic sketching on a multi-platform context: A pilot study with developers

During the past 45 years there has been a recurrence of interest on supporting sketching at electronic devices and interactive surfaces, and despite being sketching recognition fairly well addressed on the literature, the adoption of electronic sketching as a design tool is still a challenge.The current popularization of touch screen devices allows designers to sketch using their device of preference, while the current multi-platform capabilities made possible by HTML5 allows sketching systems to run on many devices at the same time. Those two factors combined might pose new opportunities for researchers to explore how designers use sketching on flexible setups by combining heterogeneous sketching devices for design sessions.This may arise new possibilities in the field of prototyping user interfaces since, by using such multi-platform systems, designers would now be able of designing interfaces for multiple devices by producing and testing them on the device itself.This paper reports a pilot experiment conducted with 6 developers, grouped into pairs on design sessions using Gambit – a multi-platform sketching system that provides a lightweight approach for prototyping user interfaces for many devices at once. We performed a discourse analysis of the professionals based on recorded videos of interviews conducted during and after design sessions with the system and aggregated the data in order to investigate the main requirements for multi-platform sketching systems.     

A constraint-based approach to spatiotemporal reasoning

We introduce a form of spatiotemporal reasoning that uses homogeneous representations of time and the three dimensions of space. The basis of our approach is Allen's temporal logic on the one hand and general constraint satisfaction algorithms on the other, where we present a new view of constraint reasoning to cope with the affordances of spatiotemporal reasoning as introduced here. As a realization for constraint reasoning, we suggest a massively parallel implementation in form of Boltzmann machines.     

参数化设计中的动态约束迭代及静态因果分析技术

参数化设计以其强有力的草图设计和图纸尺寸驱动功能成为实现产品的初步设计、系列设计以及变异式设计的核心技术。这两种参化设计算法克服了现有参数化方法在功能、效率以及可靠性等方面存在的 问题，历而能够地应用到实际系统中去。     

基于子图的草图设计和约束求解

提出了一种基于子图的拟序列化草图设计方法。基于标识的约束模型统一了二维、三维约束,使得每个几何元素对应唯一的标识,几何元素之间的约束关系表示为标识之间的约束,这些约束被分为结构约束和尺寸约束。提出了基于序列化设计过程的约束求解方法。实验表明,该技术可快速有效地进行参数化草图设计和特征编辑。     

基于推理的自动参数化图形库管理系统

本文讨论了一参数化图形管理系统ＰＤＭＳ的原理和关键技术。ＰＤＭＳ系统采用交互式草图方式定义零件原型图，采用基于推理的自动参数化方法从零件原型图中生成不同尺寸参数的零件图。ＰＤＭＳ系统不仅能用于建立参数化标准件库，而且可用于建立复杂结构的参数化非标准件库。     

Interactive Case-Based Planning for Forest Fire Management

This paper describes an AI system for planning the first attack on a forest fire. This planning system is based on two major techniques, case-based reasoning, and constraint reasoning, and is part of a decision support system called CHARADE. CHARADE is aimed at supporting the user in the whole process of forest fire management. The novelty of the proposed approach is mainly due to the use of a local similarity metric for case-based reasoning and the integration with a constraint solver in charge of temporal reasoning.