面向移动设备的各向异性纹理映射方法

为了在低性能的移动设备上实现高质量图形效果,设计实现了一种高效的各向异性纹理映射方法.首先提出了基于三角形子纹理单元精度各向异性滤波器(TSPAF),将像素表示为三角形,通过反向投影获得像素在纹理空间的三角形足迹;并在此基础上提出了一种节省带宽的混合滤波方式,利用MIPMap层选择并结合二次线性滤波和TSPAF来实现混合各向异性纹理映射.实验结果表明,该方法能获得良好的图像效果,并具有低计算量和低存储量的优点,适合移动设备GPU的实现.     

纤维可控的质感布料三维建模与服装仿真

传统布料和服装动态仿真主要通过网格模型进行模拟,并通过光照、材质和颜色设置进行渲染,布料与服装质感效果通常不能体现.本文提出一种新的基于纤维的质感布料建模与服装仿真算法.首先使用集合球约束粒子扰动的方法模拟纤维轮廓,然后根据纱线加捻的动力学和运动学原理模拟基于纤维的纱线构造方法,接着将纱线经纬编织组织结构与弹簧-质点模型结合起来,构造基于纤维块的织物布料模型,最后通过建立人体混合层次包围盒进行快速碰撞检测,实现由质感布料生成的服装动态仿真.实验结果验证了该方法可靠,有效,生成的布料能体现织物外观纤维级别的细节,对应的服装几何纹理和质感效果得到增强.     

Learning‐Based Animation of Clothing for Virtual Try‐On

This paper presents a learning‐based clothing animation method for highly efficient virtual try‐on simulation. Given a garment, we preprocess a rich database of physically‐based dressed character simulations, for multiple body shapes and animations. Then, using this database, we train a learning‐based model of cloth drape and wrinkles, as a function of body shape and dynamics. We propose a model that separates global garment fit, due to body shape, from local garment wrinkles, due to both pose dynamics and body shape. We use a recurrent neural network to regress garment wrinkles, and we achieve highly plausible nonlinear effects, in contrast to the blending artifacts suffered by previous methods. At runtime, dynamic virtual try‐on animations are produced in just a few milliseconds for garments with thousands of triangles. We show qualitative and quantitative analysis of results.     

Detail-Aware Deep Clothing Animations Infused with Multi-Source Attributes

This paper presents a novel learning-based clothing deformation method to generate rich and reasonable detailed deformations for garments worn by bodies of various shapes in various animations. In contrast to existing learning-based methods, which require numerous trained models for different garment topologies or poses and are unable to easily realize rich details, we use a unified framework to produce high fidelity deformations efficiently and easily. Specifically, we first found that the fit between the garment and the body has an important impact on the degree of folds. We then designed an attribute parser to generate detail-aware encodings and infused them into the graph neural network, therefore enhancing the discrimination of details under diverse attributes. Furthermore, to achieve better convergence and avoid overly smooth deformations, we proposed to reconstruct output to mitigate the complexity of the learning task. Experimental results show that our proposed deformation method achieves better performance over existing methods in terms of generalization ability and quality of details.     

Interactive virtual try-on clothing design systems

Clothing computer design systems include three integrated parts: garment pattern design in 2D/3D, virtual try-on and realistic clothing simulation. Some important results have been obtained in pattern design and clothing simulation since the 1980s. However, in the area of virtual try-on, only limited methods have been proposed which are applicable to some defined garment styles or under restrictive sewing assumptions. This paper presents a series of new techniques from virtually sewing up complex garment patterns on human models to visualizing design effects through physical-based real-time simulation. We first employ an hierarchy of ellipsoids to approximate human models in which the bounding ellipsoids are optimized recursively. We also present a new scheme for including contact friction and resolving collisions. Four types of user interactive operation are introduced to manipulate cloth patterns for pre-positioning, virtual sewing and later obtaining cloth simulation. In the cloth simulation, we propose a simplified cloth dynamic model and an integration scheme to realize a high quality real-time cloth simulation. We demonstrate the robustness of our proposed systems by complex garment style virtual try-on and cloth simulation.     

Natural metrics and least-committed priors for articulated tracking

In articulated tracking, one is concerned with estimating the pose of a person in every frame of a film. This pose is most often represented as a kinematic skeleton where the joint angles are the degrees of freedom. Least-committed predictive models are then phrased as a Brownian motion in joint angle space. However, the metric of the joint angle space is rather unintuitive as it ignores both bone lengths and how bones are connected. As Brownian motion is strongly linked with the underlying metric, this has severe impact on the predictive models. We introduce the spatial kinematic manifold of joint positions, which is embedded in a high dimensional Euclidean space. This Riemannian manifold inherits the metric from the embedding space, such that distances are measured as the combined physical length that joints travel during movements. We then develop a least-committed Brownian motion model on the manifold that respects the natural metric. This model is expressed in terms of a stochastic differential equation, which we solve using a novel numerical scheme. Empirically, we validate the new model in a particle filter based articulated tracking system. Here, we not only outperform the standard Brownian motion in joint angle space, we are also able to specialise the model in ways that otherwise are both difficult and expensive in joint angle space.     

Automatic pose-independent 3D garment fitting

Given a virtual garment model on a reference human model, we propose an automated 3D garment fitting system that fits the garment model to a target human model. The proposed method can transfer garment models between human models without any user guidance even when the reference and target human models have different poses. Our goal is not to resize or deform the original garment model according to the target human model but to yield realistic fitting results of the given garment on the target human models. Using pose-independent segmentation and cloth simulation, we achieve realistic and automatic fitting results in reasonable running time. Our method can replace the time-consuming manual fitting process that is necessary for many applications that use virtual garments, such as games, animations, CAD tools and online clothing stores.     

Comparison of joint angle,velocity and acceleration estimators for hydraulically actuated manipulators to a novel dynamical approach

Excavators are used for a wide range of applications like earthworks and material handling. Assistance systems are becoming more common to support the operator. For monitoring and control based assistance functions the angular position, velocity and acceleration of the joints from the working implement are required. Commercial systems often use inertial measurement units, consisting of triaxial accelerometers and gyroscopes, to accomplish an estimation of those states. A novel joint angle, velocity and acceleration estimation for hydraulic manipulators is proposed and compared to state of the art methods. A decentralized kinematic filter using no information about the underlying system and a centralized kinematic filter taking the system kinematics into account are implemented as state of the art approaches. Both filters only use inertial measurement units to obtain information about the current state of the system. The novel centralized dynamic filter uses the same information as the centralized kinematic filter and extends it by a dynamic model containing additional information about the angular acceleration due to pressure readings of the hydraulic cylinders. Kalman filtering is used to combine the derived system and measurement models with the sensor information. The methods are evaluated on a material handling excavator for single and coupled movements of the working implement. The novel centralized dynamic filter enables improvements for the angular acceleration estimation compared to the decentralized and centralized kinematic filter. Less noise of the acceleration estimation and a better tracking of the actual acceleration are shown.     

Customizing 3D garments based on volumetric deformation

Improving the reusability of design results is very important for garment design industry, since designing an elegant garment is usually labor-intensive and time-consuming. In this paper, we present a new approach for customizing 3D garment models. Our approach can transfer garment models initially dressed on a reference human model onto a target human model. To achieve this goal, firstly a spatial mapping between the two human models is established with the shape constraints of cross-sections. Secondly, the space around the clothed reference human model is tetrahedralized into five tetrahedral meshes each of which either can be worked dependently with its adjacent ones or can be worked independently. The clothed reference human model is parametrically encoded in the tetrahedral meshes. Thirdly, these tetrahedral meshes are deformed by fitting the reference human model onto the target human model by using constrained volumetric graph Laplacian deformation. The updated garment models are finally decoded from the deformed tetrahedral meshes. As a result, the updated garment models are fitted onto the target human model. Experiments show that our approach performs very well and has the potential to be used in the garment design industry.     

Modeling Garment Seam from a Single Image

We propose an automatic garment seam modeling framework to create a garment model with the seam structure from a single image. In order to achieve this, a marked seam image database and parametric seam models have been set up. Given a real seam image, we first identify the type of the seam image based on our marked seam image database and the seam parameters are parsed automatically by our sewing thread estimation method. Second the seam initial model is generated through the pre-defined parametric seam models. A garment model with the seam structure is finally obtained based on the seam position information which users have marked on the garment. Moreover, we verify the effectiveness of our method with numerous experiments.     

通用三维服装模型的强约束动态仿真方法

随着三维游戏和虚拟试衣要求的不断提高,服装仿真已经从布料模拟向服装动态模拟的方向发展,具有真实性、实时性、通用性与交互性的服装仿真技术有很强的研究和实用价值。针对目前算法研究中普遍存在的实时性与通用性不足,提出了一种针对任意三维服装模型的实时仿真方法,将模型顶点和三角面映射为质点的弹簧模型,以克服传统的布料解算器对三维模型的网格限制。利用简便易行的Verlet积分器提高运算效率,并对质点间的形变进行强约束补偿,防止过拉伸(超弹)现象的发生,提高了系统的稳定性。通过实验验证了算法的高效性和可靠性,并可方便地以插件或模块形式与其它软件整合。     

Automatic alignment for virtual fitting using 3D garment stretching and human body relocation

In recent years, researches on virtual fitting are mostly based on the data of garment pieces through Computer Aided Design. However, three-dimensional garment models are more intuitive, integrated and easy to access and manage. Therefore, we propose and design a method to automatically align virtual humans with three-dimensional garment models. Firstly, we basically align two models through three-dimensional geometric calculation and postural alteration of virtual humans. Then, we detect the penetration phenomena and define the points of the garment model penetrating into the human model as penetration points. Based on the penetration detection, we use Poisson mesh deformation to adjust the penetration points by imitating the adjustment process of dragging clothes. Finally, the results obtained from alignment can be directly used for physical-based simulation. Experimental results show that the method we propose can achieve good effects of alignment, and has good versatility and practicality.     

Physically based adaptive preconditioning for early vision

Several problems in early vision have been formulated in the past in a regularization framework. These problems, when discretized, lead to large sparse linear systems. In this paper, we present a novel physically based adaptive preconditioning technique which can be used in conjunction with a conjugate gradient algorithm to dramatically improve the speed of convergence for solving the aforementioned linear systems. A preconditioner, based on the membrane spline, or the thin plate spline, or a convex combination of the two, is termed a physically based preconditioner for obvious reasons. The adaptation of the preconditioner to an early vision problem is achieved via the explicit use of the spectral characteristics of the regularization filter in conjunction with the data. This spectral function is used to modulate the frequency characteristics of a chosen wavelet basis, and these modulated values are then used in the construction of our preconditioner. We present the preconditioner construction for three different early vision problems namely, the surface reconstruction, the shape from shading, and the optical flow computation problems. Performance of the preconditioning scheme is demonstrated via experiments on synthetic and real data sets     

Fully Convolutional Graph Neural Networks for Parametric Virtual Try-On

We present a learning-based approach for virtual try-on applications based on a fully convolutional graph neural network. In contrast to existing data-driven models, which are trained for a specific garment or mesh topology, our fully convolutional model can cope with a large family of garments, represented as parametric predefined 2D panels with arbitrary mesh topology, including long dresses, shirts, and tight tops. Under the hood, our novel geometric deep learning approach learns to drape 3D garments by decoupling the three different sources of deformations that condition the fit of clothing: garment type, target body shape, and material. Specifically, we first learn a regressor that predicts the 3D drape of the input parametric garment when worn by a mean body shape. Then, after a mesh topology optimization step where we generate a sufficient level of detail for the input garment type, we further deform the mesh to reproduce deformations caused by the target body shape. Finally, we predict fine-scale details such as wrinkles that depend mostly on the garment material. We qualitatively and quantitatively demonstrate that our fully convolutional approach outperforms existing methods in terms of generalization capabilities and memory requirements, and therefore it opens the door to more general learning-based models for virtual try-on applications.     

生物事件触发词识别方法研究

从生物文献中抽取生物事件对于生物领域的知识挖掘起着重要的作用,而事件触发词的识别是生物事件抽取的一个关键步骤。系统分别采用词汇及其上下文特征、短语标记特征、词聚类特征以及统计的词典特征构造不同的基于词级的CRF模型,用于生物事件触发词的标记。然后针对不同的触发词类型选择对应最优的标记模型,构造了一个混合CRF模型。在BioNLP 2009 ST语料库上进行了实验评估,结果表明提出的方法取得了很好的性能,为生物事件的抽取建立了良好的基础。     

A Practical and Hierarchical Yarn-based Shading Model for Cloth

Realistic cloth rendering is a longstanding challenge in computer graphics due to the intricate geometry and hierarchical structure of cloth: Fibers form plies which in turn are combined into yarns which then are woven or knitted into fabrics. Previous fiber-based models have achieved high-quality close-up rendering, but they suffer from high computational cost, which limits their practicality. In this paper, we propose a novel hierarchical model that analytically aggregates light simulation on the fiber level by building on dual-scattering theory. Based on this, we can perform an efficient simulation of ply and yarn shading. Compared to previous methods, our approach is faster and uses less memory while preserving a similar accuracy. We demonstrate both through comparison with existing fiber-based shading models. Our yarn shading model can be applied to curves or surfaces, making it highly versatile for cloth shading. This duality paired with its simplicity and flexibility makes the model particularly useful for film and games production.     

Kinematic modeling,mobility analysis and design of wheeled mobile robots

Wheeled mobile robots (WMRs) consist of interconnections of many electromechanical systems. Their mechanical subsystem comprises primarily the platform and the wheel units. To formulate the kinematic model of this class of robots, we model the individual subsystems separately. The composite kinematic model of a WMR is then a coupling of the various kinematic submodels. We study WMRs with different wheels, i.e. offset wheels, centered wheels and dual-wheels. The study focuses on system mobility, which is derived using the functional matrix. We also identified the kinematic equivalence between the dual-wheel and the centered wheels, and some advantages of the dual-wheels over the centered wheels and offset wheels. Results suggest that WMRs with mobility less than 3 cannot track a trajectory with a discontinuous heading without incorporating a time delay, during which the wheel orientation should be changed. Moreover, the steering angles of WMRs equipped with steered wheels require proper coordination to avoid jamming of the drive subsystem. For design purposes, we aim at a kinetostatically robust WMR. The concept of kinetostatic isotropy is applied to find the location of the wheels with respect to the platform and their type in order to achieve isotropy. It is shown that WMRs with three conventional wheels can be made isotropic if the offset either vanishes or equals the radius of the wheel, and if the three wheels are mounted at the vertices of an equilateral triangle.     

Extensions of the CBMeMBer filter for joint detection,tracking, and classification of multiple maneuvering targets

This paper addresses the problem of joint detection, tracking and classification (JDTC) of multiple maneuvering targets in clutter. The multiple model cardinality balanced multi-target multi-Bernoulli (MM-CBMeMBer) filter is a promising algorithm for tracking an unknown and time-varying number of multiple maneuvering targets by utilizing a fixed set of models to match the possible motions of targets, while it exploits only the kinematic information. In this paper, the MM-CBMeMBer filter is extended to incorporate the class information and the class-dependent kinematic model sets. By following the rules of Bayesian theory and Random Finite Set (RFS), the extended multi-Bernoulli distribution is propagated recursively through prediction and update. The Sequential Monte Carlo (SMC) method is adopted to implement the proposed filter. At last, the performance of the proposed filter is examined via simulations.     

Prediction of chenille yarn and fabric abrasion resistance using radial basis function neural network models

The abrasion resistance of chenille yarn is crucially important in particular because the effect sought is always that of the velvety feel of the pile. Thus, various methods have been developed to predict chenille yarn and fabric abrasion properties. Statistical models yielded reasonably good abrasion resistance predictions. However, there is a lack of study that encompasses the scope for predicting the chenille yarn abrasion resistance with artificial neural network (ANN) models. This paper presents an intelligent modeling methodology based on ANNs for predicting the abrasion resistance of chenille yarns and fabrics. Constituent chenille yarn parameters like yarn count, pile length, twist level and pile yarn material type are used as inputs to the model. The intelligent method is based on a special kind of ANN, which uses radial basis functions as activation functions. The predictive power of the ANN model is compared with different statistical models. It is shown that the intelligent model improves prediction performance with respect to statistical models.     

部件化构建的三维服装快速编辑方法

直接设计一个三维服装模型不仅耗时而且需要专业服装设计知识。为简化这一复杂 的建模过程,提出基于部件化构建的三维服装快速编辑方法,其关键在于通过分割和融合的网格 编辑技术从已有的服装模型中快速构建新的三维服装模型。首先按照服装分类分割出不同类型的 服装部件。其次基于分割出的三维服装部件以及已有的服装模型,建立部件间以及部件与模型间 的几何约束关系,把二维均值坐标插值方法应用到三维服装网格融合中,把方程数值求解问题转 化为线性插值问题,避免求解线性方程组。最后根据柔性服装的特征,构造适于柔性服装光滑保 形变换的方法。实验结果表明,该算法在不影响融合效果的前提下可以提高融合的效率,能够有 效地实现三维服装的快速编辑。