Automatic skinning and animation of skeletal models

In this paper, we present an efficient yet easy-to-implement technique which performs automatic skinning and animation of skeletal models. At a pre-processing stage, a character model is firstly decomposed into a number of segments per bone basis, and each segment is then subdivided into several chunks. A convex cage is automatically created for each chunk. The skinning and animation of skeletal models is achieved via two steps. At the first step, by minimizing a sum of several energy terms, chunk cages are implicitly skinned to the skeleton and animated. These energies are carefully designed to prevent unnatural volume change and guarantee smooth deformation transition between adjacent cages. At the second step, the model mesh vertices, represented as the mean-value coordinates with reference to proper cage vertices, are updated via cage-based deformation technique. Our approach avoids the labor-intensive process of vertex weighting and cage generation. Given the motion of a skeleton, the character model can be animated automatically.     

Shape exploration of 3D heterogeneous models based on cages

Shape exploration of 3D heterogeneous models is essential for special effects in 3D animation and games. As heterogeneous models have different numbers of vertices and different topological structures,the mapping between source and target model may be ambiguous for deformation transfer. We propose a new framework for heterogeneous model shape exploration based on cages, which provides a feasible and fast solution to this open problem. Using a public cage as an intermediate medium, the deformation of the source models can be denoted as the position changing of the cage. When applying the cage change to the target model, rough deformation transfer can be achieved. After an optimization and interpolation to generate the explored shape of the heterogeneous target model, animation can be acquired. Our method is not only suitable for triangle meshes, but also for quadrilateral meshes or any other type of meshes. We demonstrate the validity of our scheme by a series of shape exploration experiments with different models.     

Efficient and effective cage generation by region decomposition

Cage‐based deformation has become a popular method for shape deformation in computer graphics and animation. To edit a shape first requires a cage to be built to envelop the target model which is a tedious work by manual approaches. In this paper, we develop an automatic method to generate the cage for a model using voxelization based decomposition. We first voxelize the input model, and then use the seed filling algorithm to group the inner voxels. By dilating the inner voxel groups, we decompose the model into broad regions and narrow regions. Then we construct partial cages using different strategies and unite them to get a cage. Experiment results demonstrate that our method is effective, efficient as well as robust to model transformation. Copyright © 2014 John Wiley & Sons, Ltd.     

A hierarchical multiple-view approach to three-dimensional objectrecognition

A hierarchical approach is proposed for solving the surface and vertex correspondence problems in multiple-view-based 3D object-recognition systems. The proposed scheme is a coarse-to-fine search process, and a Hopfield network is used at each stage. Compared with conventional object-matching schemes, the proposed technique provides a more general and compact formulation of the problem and a solution more suitable for parallel implementation. At the coarse search stage, the surface matching scores between the input image and each object model in the database are computed through a Hopfield network and are used to select the candidates for further consideration. At the fine search stage, the object models selected from the previous stage are fed into another Hopfield network for vertex matching. The object model that has the best surface and vertex correspondences with the input image is finally singled out as the best matched model. Experimental results are reported using both synthetic and real range images to corroborate the proposed theory.     

一种基于三维Delaunay三角化的曲面重建算法

提出一种基于三维Delaunay三角化的区域增长式曲面重建方法。该方法以空间点云的Delaunay三角化为基础,结合局部区域增长的曲面构造,较以往方法具有人为参与更少、适用范围更广的优点。算法采用增量式插入点的方式构建空间Delaunay划分,采用广度优先算法,以外接圆最小为准则从Delaunay三角化得到的四面体中抽取出合适的三角片构成曲面。该算法的设计无须计算原始点集的法矢,且孔洞系数对重建的结果影响很小,重建出的三角网格面更符合原始曲面的几何特征。无论待建曲面是否是封闭曲面,本算法均可获得较好的重建效果。     

基于图像辅助的三维模型形状检索

随着3D建模技术的快速发展,互联网上可用的3D模型库出现了爆炸式增长,越来越多的3D模型可以方便地通过网络下载使用.这直接促使了3D形状检索技术的发展,即给出特定的搜索信息,要求系统搜索出符合要求的、相似的3D模型.文章提出了一种新的3D形状检索方法,以3D模型作为输入,系统将会从模型数据库中自动检索出与输入形状最相似的模型.对于给定的输入模型以及数据库中的每一个模型,首先由计算机生成多幅在不同视角下的2D草图;然后,应用Gabor滤波器对每一幅2D草图提取图像上的局部特征,并对特征进行量化,从而得到代表该图像特征的直方图,这样对于每一个3D模型将得到多个代表该模型的直方图;最终,通过对比两个模型之间直方图的相似性,可以得到它们的相似性值,从而检索出与输入模型最相似的模型.文章所提出的方法通过采取2D图像分析方法提取能反映3D模型的特征并计算出模型之间的相似性值.经过测试,在一些公开的数据集上得到了较好的效果.     

Cover geometry design using multiple convex hulls

We present a design method to create close-fitting customized covers for given three-dimensional (3D) objects such as cameras, toys and figurines. The system first computes clustering of the input vertices using multiple convex hulls, then generates multiple convex hulls using the results. It then outputs a cover geometry to set union operation of these hulls, and the resulting intersection curves are set as seam lines. However, as some of the regions created are not necessarily suitable for flattening, the user can design seam lines by drawing and erasing. The system flattens the patches of the target cover geometry after segmentation, allowing the user to obtain a corresponding 2D pattern and sew the shapes in actual fabric. This paper’s contribution lies in its proposal of a clustering method to generate multiple convex hulls, i.e., a set of convex hulls that individually cover part of the input mesh and together cover all of it. The method is based on vertex clustering to allow handling of mesh models with poor vertex connectivity such as those obtained by 3D scanning, and accommodates conventional meshes with multiple connected components and point-based models with no connectivity information. Use of the system to design actual covers confirmed that it functions as intended.     

Automatic cage generation by improved OBBs for mesh deformation

In cage-based deformation, the most tedious task is to construct the coarse cage bounding a model. Currently, the coarse cage is constructed mainly by hand, and the construction usually takes several hours, even longer. Therefore, it is important to develop a convenient method to generate the coarse cage bounding a model. In this paper, we devise a method to construct the coarse cage automatically using the improved OBB tree, while allowing the users to modify the cage easily. Firstly, the OBB tree bounding the model is generated, where we propose an improved OBB slicing rule to make the generated OBBs close to the model it contains. Secondly, the OBBs are adjusted and merged into a whole entity by the boolean union operation. Finally, the outer surface of the entity is extracted as the coarse cage. Empirical results demonstrate the effectiveness and efficiency of the automatic coarse cage-generation method.     

A semi-interactive panorama based 3D reconstruction framework for indoor scenes

We present a semi-interactive method for 3D reconstruction specialized for indoor scenes which combines computer vision techniques with efficient interaction. We use panoramas, popularly used for visualization of indoor scenes, but clearly not able to show depth, for their great field of view, as the starting point. Exploiting user defined knowledge, in term of a rough sketch of orthogonality and parallelism in scenes, we design smart interaction techniques to semi-automatically reconstruct a scene from coarse to fine level. The framework is flexible and efficient. Users can build a coarse walls-and-floor textured model in five mouse clicks, or a detailed model showing all furniture in a couple of minutes interaction. We show results of reconstruction on four different scenes. The accuracy of the reconstructed models is quite high, around 1% error at full room scale. Thus, our framework is a good choice for applications requiring accuracy as well as application requiring a 3D impression of the scene.     

Examplar coherent 3D face reconstruction from forensic mugshot database

Reconstructing 3D face models from 2D face images is usually done by using a single reference 3D face model or some gender/ethnicity specific 3D face models. However, different persons, even those of the same gender or ethnicity, usually have significantly different faces in terms of their overall appearance, which forms the base of person recognition via faces. Consequently, existing 3D reference model based methods have limited capability of reconstructing precise 3D face models for a large variety of persons. In this paper, we propose to explore a reservoir of diverse reference models for 3D face reconstruction from forensic mugshot face images, where facial examplars coherent with the input determine the final shape estimation. Specifically, our 3D face reconstruction is formulated as an energy minimization problem with: 1) shading constraint from multiple input face images, 2) distortion and self-occlusion based color consistency between different views, and 3) depth uncertainty based smoothness constraint on adjacent pixels. The proposed energy is minimized in a coarse to fine way, where the shape refinement step is done by using a multi-label segmentation algorithm. Experimental results on challenging datasets demonstrate that the proposed algorithm is capable of recovering high quality 3D face models. We also show that our reconstructed models successfully boost face recognition accuracy.     

A 3D model perceptual feature metric based on global height field

Human visual attention system tends to be attracted to perceptual feature points on 3D model surfaces. However, purely geometric-based feature metrics may be insufficient to extract perceptual features, because they tend to detect local structure details. Intuitively, the perceptual importance degree of vertex is associated with the height of its geometry position between original model and a datum plane. So, we propose a novel and straightforward method to extract perceptually important points based on global height field. Firstly, we construct spectral domain using Laplace–Beltrami operator, and we perform spectral synthesis to reconstruct a rough approximation of the original model by adopting low-frequency coefficients, and make it as the 3D datum plane. Then, to build global height field, we calculate the Euclidean distance between vertex geometry position on original surface and the one on 3D datum plane. Finally, we set a threshold to extract perceptual feature vertices. We implement our technique on several 3D mesh models and compare our algorithm to six state-of-the-art interest points detection approaches. Experimental results demonstrate that our algorithm can accurately capture perceptually important points on arbitrary topology 3D model.     

Semi‐Automatic Conversion of 3D Shape into Flat‐Foldable Polygonal Model

This paper presents a method that can convert a given 3D mesh into a flat‐foldable model consisting of rigid panels. A previous work proposed a method to assist manual design of a single component of such flat‐foldable model, consisting of vertically‐connected side panels as well as horizontal top and bottom panels. Our method semi‐automatically generates a more complicated model that approximates the input mesh with multiple convex components. The user specifies the folding direction of each convex component and the fidelity of shape approximation. Given the user inputs, our method optimizes shapes and positions of panels of each convex component in order to make the whole model flat‐foldable. The user can check a folding animation of the output model. We demonstrate the effectiveness of our method by fabricating physical paper prototypes of flat‐foldable models.     

A level-set approach for the metamorphosis of solid models

We present a new approach to 3D shape metamorphosis. We express the interpolation of two shapes as a process where one shape deforms to maximize its similarity with another shape. The process incrementally optimizes an objective function while deforming an implicit surface model. We represent the deformable surface as a level set (iso-surface) of a densely sampled scalar function of three dimensions. Such level-set models have been shown to mimic conventional parametric deformable surface models by encoding surface movements as changes in the grayscale values of a volume data set. Thus, a well-founded mathematical structure leads to a set of procedures that describes how voxel values can be manipulated to create deformations that are represented as a sequence of volumes. The result is a 3D morphing method that offers several advantages over previous methods, including minimal need for user input, no model parameterization, flexible topology, and subvoxel accuracy     

基于多视角的高精度三维人脸重建

提出了一种多阶段优化的方法来解决基于多视角图片在未知姿态、表情以及光照条件下的高精度三维人脸重建问题.首先,通过重新渲染合成的方法将参数化模型拟合到输入的多视角图片,然后在纹理域上求解一个光流问题来获取不同视角之间的对应关系.通过对应关系可以恢复出人脸的点云,并利用基于明暗恢复几何的方法来恢复人脸细节.在真实数据以及合成数据下的实验结果表明,文中方法能够恢复出带有几何细节的高精度的三维人脸模型,并且提高了现有方法的重建精度.     

面向三维点云模型的鲁棒零水印技术

对三维点云模型零水印技术开展研究,基于三维模型形状分析、结合数据分析理论,选择具有较高稳定性的三维模型全局几何特征作为水印构造的基础,通过计算三维模型顶点范数,以顶点范数为依据建立三维模型有序顶点集,分析顶点集中顶点数目的分布情况构造水印。实验结果表明,该方法执行速度较快,可以直接应用于三维点云数据,能够很好地抵抗平移、旋转、均匀缩放、顶点重排序、噪声、简化、量化、平滑和细分等常见攻击,对剪切攻击也有一定的鲁棒性,能够满足三维模型版权保护的要求。     

3D Icons and Architectural CAD

3D computer input has been a recurring challenge to engineers developing effective CAD systems. The approach adopted in this paper attempts to address a specific type of 3D input which is applicable to architecture and some engineering design tasks. In these processes, the object being designed is often an assembly of defined components. In a conventional graphics based CAD system these components are usually represented by graphical Icons which are displayed on the graphics screen and are arranged by the user. The system described here consists of 3D modelling elements which the user physically assembles to form his design. Each modelling element contains an element processor consisting of a machine readable label, data paths and control logic. The CAD system interrogates the elements. The logic within the element processors and the data paths are then used to interrogate other adjacent elements in the model. This system can therefore be considered as a "user generated""machine readable" modelling system. In an architectural application this provides the user with a system of 3D Icons with which to model and evaluate the built environment.     

Points‐based user interface for character posing

We present a points‐based user interface for character posing. In our method, users insert a number of three‐dimensional (3D) points in a virtual environment. The system performs a linear search of a motion capture database for the best matched pose and then places the pose immediately in the virtual environment to be overlapped with the input points. For a fast and precise distance computation between the input points and the example poses from the database, we developed a closed‐form solution of the 3D points registration problem. To demonstrate the easiness and usability of our approach, we built a motion database including various kinds of human motion and conducted a user study of character posing tasks with non‐expert users. Copyright © 2016 John Wiley & Sons, Ltd.     

A Knowledge Discovery System with Support for Model Selection and Visualization

The process of knowledge discovery in databases consists of several steps that are iterative and interactive. In each application, to go through this process the user has to exploit different algorithms and their settings that usually yield multiple models. Model selection, that is, the selection of appropriate models or algorithms to achieve such models, requires meta-knowledge of algorithm/model and model performance metrics. Therefore, model selection is usually a difficult task for the user. We believe that simplifying the process of model selection for the user is crucial to the success of real-life knowledge discovery activities. As opposed to most related work that aims to automate model selection, in our view model selection is a semiautomatic process, requiring an effective collaboration between the user and the discovery system. For such a collaboration, our solution is to give the user the ability to try various alternatives and to compare competing models quantitatively by performance metrics, and qualitatively by effective visualization. This paper presents our research on model selection and visualization in the development of a knowledge discovery system called D2MS. The paper addresses the motivation of model selection in knowledge discovery and related work, gives an overview of D2MS, and describes its solution to model selection and visualization. It then presents the usefulness of D2MS model selection in two case studies of discovering medical knowledge in hospital data—on meningitis and stomach cancer—using three data mining methods of decision trees, conceptual clustering, and rule induction.     

User interfaces metamodel based on graphs

Information systems are widely used in all business areas. These systems typically integrate a set of functionalities that implement business rules and maintain databases. Users interact with these systems and use these features through user interfaces (UI). Each UI is usually composed of menus where the user can select the desired functionality, thus accessing a new UI that corresponds to the desired feature. Hence, a system normally contains multiple UIs. However, keeping consistency between these UIs of a system from a visual (organisation, component style, etc.) and behavioral perspective is usually difficult. This problem also appears in software production lines, where it would be desirable to have patterns to guide the construction and maintenance of UIs. One possible way of defining such patterns is to use model-driven engineering (MDE). In MDE, models are defined at different levels, where the bottom level is called a metamodel. The metamodel determines the main characteristics of the models of the upper levels, serving as a guideline. Each new level must adhere to the rules defined by the lower levels. This way, if anything changes in a lower level, these changes are propagated to the levels above it. The goal of this work is to define and validate a metamodel that allows the modeling of UIs of software systems, thus allowing the definition of patterns of interface and supporting system evolution. To build this metamodel, we use a graph structure. This choice is due to the fact that a UI can be easily represented as a graph, where each UI component is a vertex and edges represent dependencies between these components. Moreover, graph theory provides support for a great number of operations and transformations that can be useful for UIs. The metamodel was defined based on the investigation of patterns that occur in UIs. We used a sample of information systems containing different types of UIs to obtain such patterns. To validate the metamodel, we built the complete UI models of one new system and of four existing real systems. This shows not only the expressive power of the metamodel, but also its versatility, since our validation was conducted using different types of systems (a desktop system, a web system, mobile system, and a multiplatform system). Moreover, it also demonstrated that the proposed approach can be used not only to build new models, but also to describe existing ones (by reverse engineering).     

Deep Deformation Detail Synthesis for Thin Shell Models

In physics-based cloth animation, rich folds and detailed wrinkles are achieved at the cost of expensive computational resources and huge labor tuning. Data-driven techniques make efforts to reduce the computation significantly by utilizing a preprocessed database. One type of methods relies on human poses to synthesize fitted garments, but these methods cannot be applied to general cloth animations. Another type of methods adds details to the coarse meshes obtained through simulation, which does not have such restrictions. However, existing works usually utilize coordinate-based representations which cannot cope with large-scale deformation, and requires dense vertex correspondences between coarse and fine meshes. Moreover, as such methods only add details, they require coarse meshes to be sufficiently close to fine meshes, which can be either impossible, or require unrealistic constraints to be applied when generating fine meshes. To address these challenges, we develop a temporally and spatially as-consistent-as-possible deformation representation (named TS-ACAP) and design a DeformTransformer network to learn the mapping from low-resolution meshes to ones with fine details. This TS-ACAP representation is designed to ensure both spatial and temporal consistency for sequential large-scale deformations from cloth animations. With this TS-ACAP representation, our DeformTransformer network first utilizes two mesh-based encoders to extract the coarse and fine features using shared convolutional kernels, respectively. To transduct the coarse features to the fine ones, we leverage the spatial and temporal Transformer network that consists of vertex-level and frame-level attention mechanisms to ensure detail enhancement and temporal coherence of the prediction. Experimental results show that our method is able to produce reliable and realistic animations in various datasets at high frame rates with superior detail synthesis abilities compared to existing methods.