三维人体的草绘建模方法

提出了一种三维人体的草绘建模方法,允许用户分层次绘制人体骨架线和轮廓线草图,并快速生成三维人体模型.该方法的特征主要表现在两个方面:首先,采用层次化的人体截面模板进行形变,并使用基于距离的描述子在人体模板库中检索最符合用户绘制的模板,使结果模型更能体现人体草图特性;其次,采用参数驱动的三维人体模型生成方法,将草图轮廓特征与模板轮廓进行对应并计算三维形变参数,最后对人体模板进行形变生成三维人体模型.实验结果表明,该方法能够快速构建符合用户绘制意图的三维人体模型.     

基于截面环的服装建模技术

在人体模型特征提取的基础上,采用水平切片的方法得到人体截面环,在将服装放松量转化为空隙度后,以空隙度为参数将人体截面环变形为服装截面环,根据角度同步前进法实现基于服装截面环的曲面构建.与已有方法相比,该方法建立在基于特征的参数化截面环之上,建模更加快捷,变形更容易控制.     

面向服装设计的人体建模及人体参数化*

利用人体曲面重构法构建人体参数化模型,并对人体参数化模型进行参数化变形。人体曲面重建分为预处理和曲面生成两个步骤。预处理包括坐标调整、特征识别,然后利用人体切片技术和曲面光顺技术得到人体曲面和人体参数化模型。对参数化人体模型施加尺寸变形和插值变形两种参数化变形手段,得到个性化人体和系列化人体,从而为服装设计提供很好的模型支撑。     

服装CAD中个性化三维人体建模

针对三维服装仿真中对各种不同体态特征的人体模型的需求,给出了一种个性化三维人体建模方法。首先对一系列具有不同特征尺寸的成年女性的人体扫描数据进行简化处理,建立具有一致拓扑的人体模型;然后根据不同人体的对应数据点及其相应的特征尺寸,生成各个简化数据点随特征尺寸变化的规律。利用此变化特性,对参考人体模型进行变形得到新尺寸下的人体模型。该方法已在所开发的三维虚拟试衣系统实现,并取得了较为理想的试验效果。     

变形图驱动的人体与脸部网格模板拟合系统

为了建立统一的人体模型数据库/人脸模型数据库,实现了一个用标准三维人体/人脸网格模型拟合扫描数据的系统.该系统为人体模型构建特征点候选区域,用马尔可夫网络对候选区域进行概率预测得到人体特征点的位置;对于人脸模型,采用基于回归树的算法在多幅不同角度的人脸图像上分别检测其二维特征点,融合得到准确的三维特征点位置;得到特征点后,使用相似变换对标准模板和扫描模型的位置朝向以及尺度进行统一;通过特征点引导的变形图算法对标准模板和扫描模型的形状和姿态进行粗配准;最后使用基于稠密点对应的顶点仿射变换拟合得到变形后的标准模板.对CAESAR数据集中的人体模型以及扫描得到的人体和人脸模型均进行了拟合,实验结果表明,该系统能够精确地捕捉扫描数据的几何形状.     

基于二维点云图的三维人体建模方法

近年来基于二维图像的三维建模方法取得了快速发展,但就人体建模而言,由于摄像头采集到的二维人体图像包含衣物、发丝等大量的纹理信息,而像虚拟试衣等相关应用需要将人体表面的衣物褶皱等纹理信息去除,同时考虑到裸体数据采集侵犯了用户的隐私,因此提出一种基于二维点云图像到三维人体模型的新型建模方法。与摄像机等辅助设备进行二维图片数据集的采集不同,该算法的输入是由三维人体点云模型以顶点模式绘制的二维点云渲染图。主要工作是建立一个由二维点云图和相应的人体黑白二值图构成的数据集,并训练一个由前者生成后者的生成对抗网络模型。该模型将二维点云图转化为相应的黑白二值图。将该二值图输入一个训练好的卷积神经网络,用于评估二维图像到三维人体模型构建的效果。考虑到由不完整三维点云数据重建完整的三维人体网格模型是一个具有挑战性的问题,因此通过模拟二维点云的破损和残缺状态,使得算法能够处理不完整的二维点云图。大量的实验结果表明,该方法重建出的三维人体模型能够有效实现视觉上的真实感,为了对重建后的精度进行定量的分析,选取了人体特征中具有代表性的腰围特征作为误差评估;为了增加三维人体模型库中人体形态的多样性,还引入一种便捷的三维人体模型数据增强技术。实验结果表明,该算法只需要输入一张二维点云图像,就能快速创建出相应的数字化人体模型。     

服装CAD中三维人体模型的参数化研究

针对三角网格曲面表示的3D人体模型缺少语义信息，提出一种3D人体模型的参数化方法：首先通过三角面片求交的采样策略得到采样点，然后使用B样条曲线构造人体轮廓线，最后由用户交互得到3D人体模型的参数化信息，建立3D人体模型的参数化模板．这样，在参数化人体模型模板的基础上，可以根据用户所输入的特定人体参数信息，动态地调整轮廓线和重建人体模型体表曲面，快速生成逼真的3D人体模型，从而满足服装CAD中根据用户身材尺寸大小定制服装的应用需求．     

个性化三维人体模型快速建模方法

采用模型重用的思想,通过输入21个人体测量学参数对标准人体模型进行编辑,实时获得相应体型的个性化三维人体模型．该方法使得编辑过程能够实时完成;生成的人体模型可以方便地驱动;精选的21个人体测量学参数覆盖了人体各处的细节,能够比较完整地描述人体的外形特征,满足对人体模型个性化的需求．     

基于特征线的三维服装部件参数化造型

基于特征线的服装三维造型方法有诸多优点,但是现有服装模型并不能很好地支持服装参数化设计.为此将参数化造型方法引入三维服装部件造型中,以得到参数化的服装部件.基于光顺人体模型,依据服装部件特点设计服装特征线,将特征线分为截面环和轮廓线,依次通过截面环和轮廓线的生成与调整、特征线综合调整和特征线添加约束3个步骤,得到服装特征线框架;并对该框架利用曲面插值方法得到服装曲面模型.实例结果表明,文中方法功能强大、方便灵活.     

面向服装CAD的多因素驱动人体模型变形技术研究

在以人体模型为基础的3维服装CAD系统中,为了获得设计师所需形体尺寸各异的人体模型,提出了一种多因素驱动人体模型变形的方法.该方法将人体模型的变形驱动因素分为尺寸因素、姿态因素和局部体形因素3类,并相应地提出了尺寸驱动、姿态驱动及局部体形驱动的人体模型变形算法.其中尺寸驱动采用基于截面环的 算法和基于模板插值的算法,通过对人体特征尺寸进行改变来驱动人体变形;姿态驱动是通过关节变形算法来实现特定姿态的变形,并通过建立姿态库,以实现快速姿态匹配;局部体形驱动包括基于特征面尺寸和基于特征面形状的调整,以得到具有局部特征的人体.实例表明,该方法可对已有的人体进行快速变形,以获得用户所需的人体模型,从而满足了服装CAD中对人体模型的多样性需求.     

Constructing 3D human model from front and side images

Constructing 3D human model from 2D images provides a cost-effective approach to visualize digital human in virtual environment. This paper presents a systematic approach for constructing 3D human model using the front and side images of a person. The silhouettes of human body are first detected and the feature points on the silhouettes are subsequently identified. The feature points are further used to obtain the body dimensions that are necessary for identifying a template 3D human model. The shape of the template human model can be modified by the free-form deformation method. Moreover, the proposed approach has been applied for constructing the 3D human models of 30 subjects. The comparisons between the constructed 3D models and the 3D scanning models of the 30 subjects indicate that the proposed system is very effective and robust.     

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.     

Extending 3D Lucas–Kanade tracking with adaptive templates for head pose estimation

The Lucas–Kanade tracker (LKT) is a commonly used method to track target objects over 2D images. The key principle behind the object tracking of an LKT is to warp the object appearance so as to minimize the difference between the warped object’s appearance and a pre-stored template. Accordingly, the 2D pose of the tracked object in terms of translation, rotation, and scaling can be recovered from the warping. To extend the LKT for 3D pose estimation, a model-based 3D LKT assumes a 3D geometric model for the target object in the 3D space and tries to infer the 3D object motion by minimizing the difference between the projected 2D image of the 3D object and the pre-stored 2D image template. In this paper, we propose an extended model-based 3D LKT for estimating 3D head poses by tracking human heads on video sequences. In contrast to the original model-based 3D LKT, which uses a template with each pixel represented by a single intensity value, the proposed model-based 3D LKT exploits an adaptive template with each template pixel modeled by a continuously updated Gaussian distribution during head tracking. This probabilistic template modeling improves the tracker’s ability to handle temporal fluctuation of pixels caused by continuous environmental changes such as varying illumination and dynamic backgrounds. Due to the new probabilistic template modeling, we reformulate the head pose estimation as a maximum likelihood estimation problem, rather than the original difference minimization procedure. Based on the new formulation, an algorithm to estimate the best head pose is derived. The experimental results show that the proposed extended model-based 3D LKT achieves higher accuracy and reliability than the conventional one does. Particularly, the proposed LKT is very effective in handling varying illumination, which cannot be well handled in the original LKT.     

基于网格变形的从图像重建三维人脸

从图像重建高质量三维人脸一直是计算机视觉和图形学的一个重要研究问题.不同于传统的基于立体匹配的窄基线多视几何和数据驱动的人脸形变方法,提出一种结合网格变形技术和立体视觉原理的、从图像重建高质量三维人脸模型方法.给定从不同视角拍摄的几幅人脸图像,基于健壮图像特征获得可靠的相机外部参数和稀疏三维点;在此基础上,提出一种结合几何细节保持和图像一致性约束的三维人脸变形算法重建三维人脸,通过对人脸模板的网格变形,使得变形人脸在多幅图像中的可见投影具有一致性的图像颜色强度.基于模板的人脸变形可以有效地解决三维模型成像中的遮挡问题,采用健壮估计法消除噪声、离群点和光照对目标函数收敛性的影响,对目标函数的多次非线性优化求解进一步改进了人脸重建的质量.采用合成人脸图像和真实人脸图像重建三维人脸的实验结果表明,文中算法可以从几幅宽基线图像重建高质量的三维人脸模型.     

An implementation of a garment-fitting simulation system using laser scanned 3D body data

We propose a garment-fitting system for an online retail model, which uses a consumer's 3D body data for garment fitting. This system uses front and back images to model the garment and 3D laser scanned body data to model the body. In order to recognize characteristic points on the 3D body data, a moment template composed of central moments of vector angle sets on 3D body data is proposed, and an implementation combining the 3D data and garment images is reported, which includes modeling, collision detection and feedback handling. The resulting system would support an online retail business model for garments. In the proposed business model, a body data center would scan the body and store the 3D data, the simulated garment-fitting program would be provided to individual consumers for fitting on a home PC, and retail shops would exhibit garment images on their websites. In this proposed model, security of personal data and computational cost will not be an issue.     

使用多视图L1跟踪器的三维人体运动恢复

近年来从视频中恢复三维人体运动的研究发展很快,其中大部分方法是基于前景轮廓的。提出了一种基于纹理信息的三维人体运动恢复方法,并给出了一个鲁棒、自适应的跟踪器模型。该模型基于L1跟踪器,并将其扩展到多个视图中,使用分层搜索来跟踪人体的各个部位。它可以寻找在模板子空间里重构误差最小的跟踪目标,将每个视图的重构误差作为衡量人体三维姿态与图像拟合的可能性函数。整个算法在退火粒子滤波的框架下进行。为了提高跟踪准度,在纹理模板更新过程中使用了两种方法:用人体的三维模型来检测自遮挡;根据模板系数检测计算错误的跟踪结果。综合这两种检测器,可以防止遮挡后和计算错误的跟踪结果加入到纹理模板中。在HumanEva-Ⅱ测试集上的实验表明,该算法能够得到较好的结果。     

A template-based reconstruction of plane-symmetric 3D models from freehand sketches

This paper presents a method for reconstructing a 3D model from a freehand sketch. There are two methods used in sketch-based modeling research: gestural modeling and reconstructional modeling. This research involves the reconstructional modeling method of Mitani, which was originally designed for a box-shaped model using a predefined template. Here, this method is improved by leveraging a relational template and a template matching method that extend the range of categories of the reconstructed objects. Sketch preprocessing details are provided and the template-based reconstructional method then uses the sketch preprocessing results to reconstruct a 3D model from a freehand sketch.     

人体几何建模方法综述

人体建模是计算机图形学与计算机视觉领域的重要研究课题,而人体几何建模则是人体建模的基础。人体几何建模技术发展至今,已经出现了大量的实现方法。回顾和总结了人体几何建模领域一些最新的研究成果,将其分为直接建模方法、2D图片识别方法、模板匹配方法、统计综合建模4大类,并且对人体几何建模方法的未来发展趋势进行了展望。     

Observation-oriented silhouette-aware fast full body tracking with Kinect

We present a novel approach to track full human body mesh with a single depth camera, e.g. Microsoft Kinect, using a template body model. The proposed observation-oriented tracking mainly targets at fitting the body mesh silhouette to the 2D user boundary in video stream by deforming the body. It is fast to be integrated into real-time or interactive applications, which is impossible with traditional iterative optimization based approaches. Our method is a composite of two main stages: user-specific body shape estimation and on-line body tracking. We first develop a novel method to fit a 3D morphable human model to the actual body shape of the user in front of the depth camera. A strategy, making use of two constrains, i.e. point clouds from depth images and correspondence between foreground user mask contour and the boundary of projected body model, is designed. On-line tracking is made possible in successive steps. At each frame, the joint angles of template skeleton are optimized towards the captured Kinect skeleton. Then, the aforementioned contour correspondence is adopted to adjust the projected body model vertices towards the contour points of foreground user mask, using a Laplacian deformation technique. Experimental results show that our method achieves fast and high quality tracking. We also show that the proposed method is benefit to three applications: virtual try-on, full human body scanning and applications in manufacturing systems.