表演驱动的矢量化二维表情动画

为了方便快捷生成生动的卡通表情动画,提出将表情数据重定向到卡通形象上的算法.该算法由用户在卡通形象上标记出与表情数据相对应拓扑结构的控制点,以此控制点集合与表情数据首帧控制点集合做比对;使用得到的比例关系将后续表情数据重定向到卡通形象上,从而形成针对卡通形象的表情数据.实验结果表明,运用文中算法可以制作出较为生动形象的卡通表情动画.     

改进鱼眼变换技术的图像适应

目的 为解决目前基于鱼眼变换技术的图像适应方法难以解决的焦点检测和多焦点冲突两大问题,提出一种基于改进鱼眼变换技术的图像适应方法。方法 提出的方法根据源图像的能量计算出图像中所有最优高能量线并组成高能量线集合,作为源图像的高能量部分,即图像的焦点区域;以能量线而不是传统的图像区域为单位进行鱼眼变换以得到目标图像。结果 改变鱼眼变换技术的变换模式并应用于图像适应中,实验结果表明,本文方法解决了基于鱼眼变换技术的图像适应方法存在的问题,通过本文算法所得到的目标图像具有较好的视觉效果,用户满意度接近4分。算法运行速度较快,将源图像(512×384)长度缩小一半的情况下仅需6 s的运算时间。结论 本文方法一方面保留了鱼眼变换图像适应方法的优势,在突出显示图像重要部分的同时,不会忽略图像的次要部分;另一方面解决了鱼眼变换图像适应方法存在的焦点检测和多焦点冲突问题。实现效果和用户主观评价结果表明,该方法是一种有效可行的图像适应方法。     

Efficient random saliency map detection

Most image retargeting algorithms rely heavily on valid saliency map detection to proceed. However, the inefficiency of high quality saliency map detection severely restricts the application of these image retargeting methods. In this paper, we propose a random algorithm for efficient context-aware saliency map detection. Our method is a multiple level saliency map detection algorithm that integrates multiple level coarse saliency maps into the resulting saliency map and selectively updates unreliable regio...     

Binding Virtual Environments to Toolkit Capabilities

There are many toolkits and development environments that aid the process of constructing virtual environment applications. Many of these development environments encourage customising a virtual environment's design while rapid prototyping within the confines of a toolkit's capabilities. Thus the choice of the technology and its associated support has been made independent of the end-use requirements of the final system. This can bias a virtual environment's design by implementation based constraints. We propose that an alternative approach is the consideration of virtual environment requirements in the context of an inspectable design model, to identify the requirements that a toolkit will need to support. In the context of an example, we present a selection of design requirements that we consider important for virtual environment design in general. We explore how these requirements might be mapped to different capabilities using Virtual Reality Modelling Language (VRML) as a concrete example of a platform technology.     

A Novel Approach Makes Higher Order Wavelets Really Efficient for Radiosity

Since wavelets were introduced in the radiosity algorithm ⁵, surprisingly little research has been devoted to higher order wavelets and their use in radiosity algorithms. A previous study ¹³ has shown that wavelet radiosity, and especially higher order wavelet radiosity was not bringing significant improvements over hierarchical radiosity and was having a very important extra memory cost, thus prohibiting any effective computation. In this paper, we present a new implementation of wavelets in the radiosity algorithm, that is substantially different from previous implementations in several key areas (refinement oracle, link storage, resolution algorithm). We show that, with this implementation, higher order wavelets are actually bringing an improvement over standard hierarchical radiosity and lower order wavelets.     

Interpolatory √3-Subdivision

We present a new interpolatory subdivision scheme for triangle meshes. Instead of splitting each edge and performing a 1-to-4 split for every triangle we compute a new vertex for every triangle and retriangulate the old and the new vertices. Using this refinement operator the number of triangles only triples in each step. New vertices are computed with a Butterfly like scheme. In order to obtain overall smooth surfaces special rules are necessary in the neighborhood of extraordinary vertices. The scheme is suitable for adaptive refinement by using an easy forward strategy. No temporary triangles are produced here which allows simpler data structures and makes the scheme easy to implement.     

面向广电节目的虚拟人手语合成显示平台研究

基于中国手语合成技术的虚拟人手语视频显示平台技术是一个全新的课题.为了满足广电新闻节目对手势运动流畅性要求,实现了一种上下文相关的手势运动平滑算法,该方法能够充分利用前后两帧的差异来实现手势运动的平滑过渡,其视觉感观效果较传统插值算法更加平滑自然;同时提出了一种基于统计和规则相结合的手势运动重定向算法,在统计方法的基础上针对不同骨架大小以及运动特性进行规则约束,使得标准模型手势运动数据应用到新模型上而不失其准确性;最后,通过扩展基本手语词表达形式并基于alpha融合技术实现了面向广电新闻节目的虚拟人手语合成显示平台并取得很好的结果.     

结合双向相似性变换的重定向图像质量评价

目的 显示设备的多样化使得图像重定向的作用日益凸显。不同的重定向方法产生不同视觉感受的重定向图像,而如何评价重定向图像的质量,优化重定向算法是当前研究的热点与难点,为此,提出一种结合双向相似性变换的重定向图像质量评价方法。方法 首先对原始图像和重定向图像进行像素点双向匹配,利用网格顶点坐标对计算前向变换矩阵和后向变换矩阵。然后由相似性变换矩阵与标准变换矩阵间的距离得到重定向图像的几何失真。由网格面积缺失得到重定向图像的信息损失。最后结合网格的显著性,融合前向匹配与后向匹配的几何失真和信息损失得到重定向图像的质量。结果 该方法在RetargetMe和CUHK数据库上的KRCC（Kendall rank correlation coefficient）和SROCC（Spearman rank-order correlation coefficient）性能分别达到了0.46和0.71,较现有方法有较大提升。在前向匹配与后向匹配测试中,双向匹配的测试结果优于单向匹配。结论 本文方法将图像的重定向处理看做相似性变换过程。实验结果表明,从相似性变换矩阵中提取的相关特征能够较精确度量重定向图像的几何失真,而由此引发的网格面积缺失也能准确反映出重定向图像的信息损失。另外,采用双向匹配机制一定程度上减少了像素匹配误差对实验结果的影响,有效提升了重定向图像质量预测的准确性。该方法对重定向图像的质量评价效果好,适用于重定向图像的质量预测及算法优化。     

Cluster-Based Saliency-Guided Content-Aware Image Retargeting

Straightforward image resizing operators without considering image contents (e.g., uniform scaling) cannot usually produce satisfactory results, while content-aware image retargeting aims to arbitrarily change image size while preserving visually prominent features. In this paper, a cluster-based saliency-guided seam carving algorithm for content-aware image retargeting is proposed. To cope with the main drawback of the original seam carving algorithm relying on only gradient-based image importance map, we integrate a gradient-based map and a cluster-based saliency map to generate a more reliable importance map, resulting in better single image retargeting results. Experimental results have demonstrated the efficacy of the proposed algorithm.     

Motion retargeting and evaluation for VR-based training of free motions

Virtual reality (VR) has emerged as one of the important and effective tools for education and training. Most VR-based training systems are situation based, where the trainees are trained for discrete decision making in special situations presented by the VR environments. In contrast, this paper discusses the application of VR to a different class of training, for learning free motion, often required in sports and the arts. We propose a VR-based motion-training framework that contains an intuitive motion-guiding interface, posture-oriented motion retargeting, and an evaluation and advice scheme for corrective feedback. Applications of the proposed framework to simple fencing training and a dance imitation game are demonstrated.