人脸漫画特征关系夸张及相像度优化

提出一种漫画中人脸特征的夸张以及相像度优化算法.夸张部分不仅比较了不同漫画对象同一特征之间的相互关系,还比较了同一漫画对象里不同特征之间的相互关系,使得夸张更加具有对比度.引入一种相像度测量方法,以反映漫画结果与原始照片之间的相似性.根据计算得到的"相像度",进一步优化人脸特征之间的夸张.分析与实验表明,该方法生成的漫画具有较好的艺术效果.     

漫画风格的人脸肖像生成算法

为模拟艺术家画出的具有夸张效果的肖像漫画,由用户输入正面人脸照片,通过交互获取关键特征点,根据特征点计算面部特征值来判断需要夸张的部分和各自的夸张方式;然后根据特征点自动生成不同层级的网格并分层实施夸张变形;最后进行图像处理以获得不同艺术风格的图像.该算法从研究漫画家的作画风格入手,总结了肖像漫画特定的夸张规律,所生成的漫画风格人脸肖像效果较好,能够应用于非真实感图形学和数字娱乐等领域.     

参数化的肖像漫画生成算法

现有计算机生成漫画的方法大多基于高层语义描述和图像模板的方式来实现,主要通过基于图像变形的算法达到漫画夸张的效果,更多关注的是夸张点的位置模板和夸张的比例,很少从艺术家的绘画本质,即线条来描述夸张的尺度。参数化的方法从艺术家绘画的本质线条出发,分析夸张的基本原理,构建组成人脸夸张各器官的线条元素,将漫画的夸张特征转换为一些可控制的参数,并通过局部参数的控制调整,实现不同艺术风格的漫画。实验证明该方法实现的漫画效果线条造型丰富,夸张效果突出,较好地还原了艺术家漫画夸张的线条表现本质。     

基于相关分析的肖像素描漫画生成系统

目前,计算机生成肖像漫画的方法尚不能从漫画作品中有效地学习到人物五官之间的位置关系及相互作用,其生成的肖像漫画不够协调、生动。为此,通过分析人脸肖像漫画的作画规律,提出一种基于相关分析的肖像漫画生成方法。该方法从研究漫画家的作画风格着手,通过形状夸张和关系夸张来协调五官的位置关系及其相互作用,所生成的肖像漫画更为生动、形象,具有较好的协调性。通过与一种简单有效的非真实渲染方法结合,最终实现一个素描漫画生成系统。     

计算机肖像漫画方法综述

肖像漫画因其能生动地对漫画对象的特点进行夸张,而在报纸等媒体中广泛使用.以计算机漫画创作流程为主线对计算机漫画创作方法的基本思想和关键技术进行归纳与分析,重点介绍了目前几种有关特征夸张的理论方法,即用户手动确定夸张方式、模板夸张、根据漫画家的创作规则进行夸张以及机器学习方法捕捉漫画家的规则等四种方法.最后阐述了有关特征夸张理论的未来发展趋势.     

面向移动的卡通人脸生成系统

本文给出了一个面向移动数字娱乐的肖像漫画生成系统。该系统的输入是一张真实人脸照片，输出为具有娱乐效果的夸张人脸肖像。主要研究内容包括；第一，人脸照片的肖像插图画的生成。文中采用了Unsharp Mask锐化处理结合色彩缩放运算的方法，本方法不仅考虑到移动设备用户对计算速度的要求，而且能保留人脸的绝大部分特征，从而更为有效地生成人脸的肖像插图画。第二，人脸表情变形以产生人物的幽默漫画。对基于特征的变形方法进行了改进，使其更加自动化。此外，本文改进了传统的ASM方法，用来帮助去除人脸图像背景信息和更为方便地控制人脸上的特征点。整个系统在局域网和PDA上表现出了很好的娱乐效果。     

肖像照片漫画风格化方法

为了解决已有方法不能自动生成反映五官特征且具有写实漫画风格的线条画的问题,基于数据驱动和滤波的混合方法,提出一种漫画风格肖像线条画自动生成的方法.将五官和头发分为2部分,基于数据驱动的方法合成五官,使用非数据驱动的方法生成头发.在已有的特征点基础上,从数据库中匹配合适的五官数据生成五官图片.对于头发的处理,使用Canny边缘检测、图像二值化、自适应阈值二值化和XDoG算子4种不同处理方法生成头发线条域;为了更接近绘画效果,使用不同的绘画纹理与头发线条域进行叠加,生成具有不同纹理、不同风格的头发.整合五官图片和头发图片,最终生成肖像的漫画风格线条画.从互联网上获取图片构建数据集进行实验,采用不同方法生成不同风格的图片,并请专业和非专人士分别对图像质量的高低、人物特征的把握准确程度和整体审美效果3个方面打分进行评估.结果表明,所提方法能够实时地处理发生偏侧的人脸图片,与其他方法相比,该方法能生成的图片是写实漫画风格而非卡通风格或素描风格,在生成漫画风格夸张五官的同时处理结构复杂的头发.     

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。     

人物肖像画及其卡通动画仿真系统的建立

文章主要目的是利用一台普通的个人电脑和一张人脸的正面照片来自动生成具有写实风格或者夸张效果的人物肖像漫画及其动画.AAM模型是一种统计模型,可以很好地应用于人脸的特征点定位.但是AAM模型在信息的处理上忽略了颜色信息的作用,而肤色信息在人脸检测时往往起着非常大的作用.文中主要采用的方法是先利用肤色信息减小AAM搜索的搜索范围,然后基于这种改进的AAM模型,定位照片上的人脸特征,并以此为基础设计了一个人物肖像画生成系统.该算法对近百幅人脸的正面照片进行实验,实验结果令人满意.该方法能够快速生成特定人脸的肖像画并能较好地应用于卡通动画制作向导、多媒体智能娱乐、游戏和网络即时通讯软件等领域中.     

基于生成对抗文本的人脸图像翻译

为了使得人脸图像翻译方法具有更好的翻译效果,提出了一种基于生成对抗文本的人脸图像翻译方法（T-GAN）。根据人脸的特殊性,利用深度对称结构联合编码方法,提取人脸所对应的文本描述特征。然后结合生成对抗“博弈”的思想,强迫判别网络判断生成的图像是否符合文本描述,让判别网络不仅仅能够学习生成图像和输入图像之间的关系,也能够学习生成图像和文本描述的对应关系,达到强化训练的效果。实验结果表明,本方法具有使用价值,在各种肤色、发色人脸图像翻译任务都给出了高质量的图像翻译结果,并与其他图像翻译方法相比较,翻译效果更好。     

Example-based caricature generation with exaggeration control

Caricature is a popular artistic media widely used for effective communications. The fascination of caricature lies in its expressive depiction of a person’s prominent features, which is usually realized through the so-called exaggeration technique. This paper proposes a new example-based automatic caricature generation system supporting the exaggeration of both the shape of facial components and the spatial relationships among the components. Given the photograph of a face, the system automatically computes the feature vectors representing the shape of facial components as well as the spatial relationship among the components. Those features are exaggerated and then used to search the learning database for the corresponding caricature components and for arranging the retrieved components to create the caricature. Experimental results show that our system can generate the caricatures of the example style capturing the prominent features of the subjects.     

Interactive 3D caricature from harmonic exaggeration

A common variant of caricature relies on exaggerating characteristics of a shape that differs from a reference template, usually the distinctive traits of a human portrait. This work introduces a caricature tool that interactively emphasizes the differences between two three-dimensional meshes. They are represented in the manifold harmonic basis of the shape to be caricatured, providing intrinsic controls on the deformation and its scales. It further provides a smooth localization scheme for the deformation. This lets the user edit the caricature part by part, combining different settings and models of exaggeration, all expressed in terms of harmonic filter. This formulation also allows for interactivity, rendering the resulting 3d shape in real time.     

Frontal and Semi-Frontal Facial Caricature Synthesis Using Non-Negative Matrix Factorization

In this paper, we present a novel approach to synthesizing frontal and semi-frontal cartoon-like facial caricatures from an image. The caricature is generated by warping the input face from the original feature points to the corresponding exaggerated feature points. A 3D mean face model is incorporated to facilitate face to caricatures by inferring the depth of 3D feature points and the spatial transformation. Then the 3D face is deformed by using non-negative matrix factorization and projected back to image plane for future warping. To efficiently solve the nonlinear spatial transformation, we propose a novel initialization scheme to set up Levenberg-Marquardt optimization. According to the spatial transformation, exaggeration is applied to the most salient features by exaggerating their normalized difference from the mean. Non-photorealistic rendering (NPR) based stylization completes the cartoon caricature. Experiments demonstrate that our method outperforms existing methods in terms of view angles and aesthetic visual quality.     

Facial Feature Exaggeration According to Social Psychology of Face Perception

We propose a personality trait exaggeration system emphasizing the impression of human face in images, based on multi‐level features learning and exaggeration. These features are called Personality Trait Model (PTM). Abstract level of PTM is social psychology trait of face perception such as amiable, mean, cute and so on. Concrete level of PTM is shape feature and texture feature. A training phase is presented to learn multi‐level features of faces from different images. Statistical survey is taken to label sample images with people's first impressions. From images with the same labels, we capture not only shape features but also texture features to enhance exaggeration effect. Texture feature is expressed by matrix to reflect depth of facial organs, wrinkles and so on. In application phase, original images will be exaggerated using PTM iteratively. And exaggeration rate for each iteration is constrained to keep likeness with the original face. Experimental results demonstrate that our system can emphasize chosen social psychology traits effectively.     

基于特征发现的卡通人脸肖像生成

通过对成年男女各100幅真实照片进行特征提取和特征统计，获得平均人脸特征分布信息，对新输入的人脸照片进行特征比对，发现其相对突出的特征，采用主动形状模型特征提取和特征线对相结合的方法，对突出的特征实现自动变形，生成人物的卡通肖像．实验结果表明，该方法具有人脸数据量大、特征提取和发现的自动化、变形效果好等优点．     

Manifold‐Based 3D Face Caricature Generation with Individualized Facial Feature Extraction

Caricature is an interesting art to express exaggerated views of different persons and things through drawing. The face caricature is popular and widely used for different applications. To do this, we have to properly extract unique/specialized features of a person's face. A person's facial feature not only depends on his/her natural appearance, but also the associated expression style. Therefore, we would like to extract the neutural facial features and personal expression style for different applicaions. In this paper, we represent the 3D neutral face models in BU–3DFE database by sparse signal decomposition in the training phase. With this decomposition, the sparse training data can be used for robust linear subspace modeling of public faces. For an input 3D face model, we fit the model and decompose the 3D model geometry into a neutral face and the expression deformation separately. The neutral geomertry can be further decomposed into public face and individualized facial feature. We exaggerate the facial features and the expressions by estimating the probability on the corresponding manifold. The public face, the exaggerated facial features and the exaggerated expression are combined to synthesize a 3D caricature for a 3D face model. The proposed algorithm is automatic and can effectively extract the individualized facial features from an input 3D face model to create 3D face caricature.     

面向移动数字娱乐的卡通人脸动画系统

给出了一个移动平台下的卡通人脸动画系统,其输入是一张二维真实人脸照片和一段文本,输出为具有娱乐效果的手机卡通人脸动画。首先,根据输入的照片生成人物的卡通肖像,采用了基于特征发现的卡通人脸肖像生成方法。其次,在卡通肖像的基础上结合文本驱动产生卡通人脸动画。最后,将系统移植到移动平台,在手机上播放卡通人脸动画,该系统在局域网和PDA上具有很好的娱乐动画效果。     

Perceptually-motivated shape exaggeration

Image communication would appear more efficient if the visual cases of the concerned parts can be enhanced. One way to achieve this is by local shape exaggeration in rendering. In this paper, we present an interactive scheme for controllable local shape exaggeration. Our approach achieves local, direct, and consistent appearance enhancement by modifying the surface orientation in an intuitive and globally optimized manner with sparse user-specified constraints. Compared with previous approaches, the main contribution of this paper is the introduction of adaptive exaggeration function (AEF), which is capable of modulating the extent of detail enhancement to obtain a satisfactory shape exaggeration result. The AEF model is derived based on a series of experiments. We complement our new approach with a variety of examples, user studies, and provide comparisons with recent approaches.