利用人脸特征及其关系的漫画夸张与合成

在人脸漫画中,人脸特征(脸型以及五官)形状的夸张与特征之间关系的夸张是存在差异的,而目前由计算机生成的人脸漫画算法中并未考虑这一点,为此提出一种漫画夸张与合成方法.该方法由基于样本的特征的形状夸张、基于规则的特征之间的关系夸张以及两者之间的合成3部分组成.在人脸特征的形状夸张部分不需要大量的样本库,只通过少量的漫画样本便可以捕捉形状的夸张;在人脸特征之间的关系夸张部分,引入了直观的"T型规则"方式描述人脸特征在夸张时的相互关系;在人脸形状夸张与关系夸张两者的合成部分,采用"比例"的形式来描述人脸特征以及特征之间的关系,使得夸张后可以方便地进行两者的合成.最后采用调查问卷的方式评测该方法生成的漫画效果,结果表明其效果良好.     

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.     

Shape preserving design of vibrating structures using topology optimization

In several engineering components, the shape of some functional surfaces needs to be preserved in order to avoid losing performance or even its functionality when subjected to loads. This is particularly important when tight tolerances are required for operational conditions in some regions. If the deformation significantly affects product functionality, it is interesting to use a shape preserving design technique. This will often reduce deformation in a local region. To achieve that, we deal with topology optimization of elastic, continuum structures with Rayleigh damping, subjected to time-harmonic, design-independent external dynamic loading with prescribed excitation frequency, amplitude and spatial distribution. In topology optimization for vibrating structures, the obtained design should often have its resonance frequencies driven far away from the given excitation frequency in order to avoid resonance and to reduce vibration levels. In this work, we explore harmonic vibration problems with the excitation frequency lower than the first resonance frequency of the initial structure. Dynamic compliance minimization is used to improve dynamic response of the structure. An additional local dynamic compliance constraint is used to define the shape preserving problem, thus, reducing deformation in specific regions of a part named shape preserving region (SPR). A commercial FE code (ANSYS^?) is used to solve the finite element problem. The optimization Method of Moving Asymptotes (MMA) is used with the modified Solid Isotropic Material with Penalization (SIMP) material interpolation scheme. The effectiveness of this technique is presented using 2D plane structures. Coherent results were achieved using the proposed optimization formulation. It is possible to observe significant decrease on local deformation, at expense of little increase on global dynamic compliance.     

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．     

Topology‐aware moving least square deformation for 2D characters

Deformation method based on moving least squares (MLS) allows the user to manipulate 2D characters using either sets of points or line segments in real time. However, the traditional MLS deformation spreads the deformation of the controls with respect to the spatial distance, but oblivious to the shape topology, which would possibly lead to distortion. In this paper, we present a topology‐aware MLS deformation approach for 2D characters. First, a Laplace equation is solved to obtain a set of weights, which are called harmonic weights. Then, the MLS deformation is performed by using the harmonic weights as the deformation influence of the user‐specified controls. Finally, the possible distortion in the traditional MLS deformation can be effectively avoided, as the harmonic weights spread the deformation of the controls in a localized and topology‐aware way. In addition, a simple but effective area‐preserving variant of MLS deformation is proposed, which is suitable for the editing of incompressible objects. Copyright © 2015 John Wiley & Sons, Ltd.     

Harmonic 1-form based skeleton extraction from examples

This paper presents a method to extract skeletons using examples. Our method is based on the observation that many deformations in real-world applications are isometric or near isometric. By taking advantage of the intrinsic property of harmonic 1-form, i.e., it is determined by the metric and independent of the resolution and embedding, our method can easily find a consistent mapping between the reference and example poses which can be in different resolutions and triangulations. We first construct the skeleton-like Reeb graph of a harmonic function defined on the given poses. Then by examining the changes of mean curvatures, we identify the initial locations of joints. Finally we refine the joint locations by solving a constrained optimization problem. We demonstrate the efficacy of the proposed framework by pose space deformation, skeleton transfer, shape segmentation and pose-invariant shape signature.     

Semi‐Supervised Learning in Reconstructed Manifold Space for 3D Caricature Generation

Recently, automatic 3D caricature generation has attracted much attention from both the research community and the game industry. Machine learning has been proven effective in the automatic generation of caricatures. However, the lack of 3D caricature samples makes it challenging to train a good model. This paper addresses this problem by two steps. First, the training set is enlarged by reconstructing 3D caricatures. We reconstruct 3D caricatures based on some 2D caricature samples with a Principal Component Analysis (PCA)‐based method. Secondly, between the 2D real faces and the enlarged 3D caricatures, a regressive model is learnt by the semi‐supervised manifold regularization (MR) method. We then predict 3D caricatures for 2D real faces with the learnt model. The experiments show that our novel approach synthesizes the 3D caricature more effectively than traditional methods. Moreover, our system has been applied successfully in a massive multi‐user educational game to provide human‐like avatars.     

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.     

Shape Decomposition using Modal Analysis

We introduce a novel algorithm that decomposes a deformable shape into meaningful parts requiring only a single input pose. Using modal analysis, we are able to identify parts of the shape that tend to move rigidly. We define a deformation energy on the shape, enabling modal analysis to find the typical deformations of the shape. We then find a decomposition of the shape such that the typical deformations can be well approximated with deformation fields that are rigid in each part of the decomposition. We optimize for the best decomposition, which captures how the shape deforms. A hierarchical refinement scheme makes it possible to compute more detailed decompositions for some parts of the shape.
Although our algorithm does not require user intervention, it is possible to control the process by directly changing the deformation energy, or interactively refining the decomposition as necessary. Due to the construction of the energy function and the properties of modal analysis, the computed decompositions are robust to changes in pose as well as meshing, noise, and even imperfections such as small holes in the surface.     

球面调和描述子在图像形状匹配中的应用

球面调和分析是球面信号分析的重要工具, 本文采用球面调和描述子对图像进行形状匹配. 首先把平面图像映射到球面上, 然后计算球面图像的球面调和描述子, 最后通过球面调和描述子得到平面图像的相似性. 实验结果表明, 球面调和描述子可以较好地匹配图像的形状相似性, 并且具有旋转和比例不变性.     

Deformable part inspection using a spring–mass system

In order to inspect deformable parts, recent works use virtual deformation on a digitized version of a real-part to bring the part model back to its nominal shape. This simulation mimics the real process called fixturing, which is normally used by the manufacturer to bring back the part into its nominal shape once installed. To perform such virtual deformation Finite Element Methods (FEMs) are used in order to meet the precision requirements of the inspection process. This paper presents a method based on a spring–mass system, whose formulation is much simpler than the FEM, which allows the calculation of deformations of shell type parts with accuracy comparable to FEM. Furthermore, due to the simplicity in its formulation the algorithm can be implemented more easily than the FEM. The system is composed of two types of springs: one type models membrane behavior of the part’s mesh model and the second type models the flexion behavior between each mesh elements. We show that by applying the proposed mass-spring model, it is possible to reduce the calculation time by 80% over standard FEM calculation opening the door to real-time inspection.     

从宫崎骏的感官世界看中国动漫产业发展之瓶颈

如果说文化产业是“朝阳产业”,动漫产业则是这轮朝阳上绚丽的霞光。动漫产业,是指以“创意”为核心,以动画、漫画为表现形式,包含动漫图书、报刊、电影、电视、音像制品以及生产和经营与动漫形象有关的衍生产品的产业。面对资金、技术、人才、创意、市场、体制等中国动漫业的诸多瓶颈,我们需要更深入的思考。     

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。     

Topology preserved shape deformation

This paper presents a novel framework for image and shape deformation, and applies the presented method to 2D shape deformation and image/video magnifying. Our proposed framework maintains two distinct advantages. The first is to enforce the topology preservation constraints on a given displacement field. This allows us to develop a foldover-free constrained deformation approach. The second is the ability to easily incorporate the constraint of As-Rigid-As Possible deformation. It guarantees that the resulting distortions are as small as possible. Experiments are carried out on both 2D shape deformations and images/video magnifying.     

Deformation‐Driven Shape Correspondence

Non‐rigid 3D shape correspondence is a fundamental and difficult problem. Most applications which require a correspondence rely on manually selected markers. Without user assistance, the performances of existing automatic correspondence methods depend strongly on a good initial shape alignment or shape prior, and they generally do not tolerate large shape variations. We present an automatic feature correspondence algorithm capable of handling large, non‐rigid shape variations, as well as partial matching. This is made possible by leveraging the power of state‐of‐the‐art mesh deformation techniques and relying on a combinatorial tree traversal for correspondence search. The search is deformation‐driven, prioritized by a self‐distortion energy measured on meshes deformed according to a given correspondence. We demonstrate the ability of our approach to naturally match shapes which differ in pose, local scale, part decomposition, and geometric detail through numerous examples.     

Smooth Shape‐Aware Functions with Controlled Extrema

Functions that optimize Laplacian‐based energies have become popular in geometry processing, e.g. for shape deformation, smoothing, multiscale kernel construction and interpolation. Minimizers of Dirichlet energies, or solutions of Laplace equations, are harmonic functions that enjoy the maximum principle, ensuring no spurious local extrema in the interior of the solved domain occur. However, these functions are only C⁰ at the constrained points, which often causes smoothness problems. For this reason, many applications optimize higher‐order Laplacian energies such as biharmonic or triharmonic. Their minimizers exhibit increasing orders of continuity but lose the maximum principle and show oscillations. In this work, we identify characteristic artifacts caused by spurious local extrema, and provide a framework for minimizing quadratic energies on manifolds while constraining the solution to obey the maximum principle in the solved region. Our framework allows the user to specify locations and values of desired local maxima and minima, while preventing any other local extrema. We demonstrate our method on the smoothness energies corresponding to popular polyharmonic functions and show its usefulness for fast handle‐based shape deformation, controllable color diffusion, and topologically‐constrained data smoothing.     

Stratification approach for 3-D euclidean reconstruction of nonrigid objects from uncalibrated image sequences.

This paper addresses the problem of 3-D reconstruction of nonrigid objects from uncalibrated image sequences. Under the assumption of affine camera and that the nonrigid object is composed of a rigid part and a deformation part, we propose a stratification approach to recover the structure of nonrigid objects by first reconstructing the structure in affine space and then upgrading it to the Euclidean space. The novelty and main features of the method lies in several aspects. First, we propose a deformation weight constraint to the problem and prove the invariability between the recovered structure and shape bases under this constraint. The constraint was not observed by previous studies. Second, we propose a constrained power factorization algorithm to recover the deformation structure in affine space. The algorithm overcomes some limitations of a previous singular-value-decomposition-based method. It can even work with missing data in the tracking matrix. Third, we propose to separate the rigid features from the deformation ones in 3-D affine space, which makes the detection more accurate and robust. The stratification matrix is estimated from the rigid features, which may relax the influence of large tracking errors in the deformation part. Extensive experiments on synthetic data and real sequences validate the proposed method and show improvements over existing solutions.