Stereo Video Retargeting with Representative Seams in a Group of Stereoscopic Frames

The important requirements for stereo video retargeting are threefold: keeping temporal coherence, preventing depth distortion, and minimizing shape distortions of the retargeted video. To meet these requirements, the left and right video sequences are divided into groups of frames (GoFs), where the GoF is a basic unit for the seam carving and we assign a set of fixed seams for all frames within the GoF. To determine the fixed seams for each GoF, we need to find the GoF boundary in the video first. Then, the representative frame for each GoF is generated by considering the spatial saliency and temporal coherence. Also, the confidence of the stereoscopic correspondence between the left and right frames is considered to prevent depth distortion.     

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。     

基于自适应网格变形的图像编辑算法

提出一套基于自适应网格变形的图像编辑算法框架,包括图像中特征物的平移、旋转和变形,以及保持特征物的任意几何边界图像适应.该算法将图像表示为基于图像特征的自适应三角网格,由此将图像编辑问题转换为带约束的网格变形问题.网格变形由一个二次型能量函数所控制,特征物的平移、旋转和变形可以表述为该能量优化问题的约束;代表特征物的三角网格在网格变形过程中只允许发生刚性变换.该能量优化问题的全局最优解可以通过求解1个或多个稀疏方程组得到.实验结果表明,该算法效果理想、鲁棒性好、运行效率高,可以有效地应用于图像处理软件中.     

重要区域保持的图像缩放质量评价方法

目的 图像缩放质量评价是评估图像非等比例缩放优劣的依据,现有主流评价方法不能客观有效地给出定量评价结果,为此提出一种基于重要区域保持的图像非等比例缩放评价方法。方法 首先,结合视觉显著度、图像边缘和超像素分割构造重要区域识别算法;然后,设计描述图像缩放前后重要区域大小和内容保持的面积变化函数和成分变化函数;最后混合两种函数提出缩放质量评价函数。结果 在RetargetMe提供的标准测试集上对本文方法进行实验验证,计算缩放质量值以评价不同缩放方法的优劣,并利用肯德尔系数度量本文方法的评价结果与主观评价的一致性,本文方法的平均肯德尔系数比当前主流客观方法高0.5%~11%。结论 与现有主流客观评价方法相比,本文方法所得到的肯德尔系数值更大,证明该方法能够更准确有效、快速、定量地评价各类图像非等比例缩放结果。     

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.     

Salient edge and region aware image retargeting

The purpose of image retargeting is to automatically adapt a given image to fit the size of various displays without introducing severe visual distortions. The seam carving method can effectively achieve this task and it needs to define image importance to detect the salient context of images. In this paper we present a new image importance map and a new seam criterion for image retargeting. We first decompose an image into a cartoon and a texture part. The higher order statistics (HOS) on the cartoon part provide reliable salient edges. We construct a salient object window and a distance dependent weight to modify the HOS. The weighted HOS effectively protects salient objects from distortion by seam carving. We also propose a new seam criterion which tends to spread seam uniformly in nonsallient regions and helps to preserve large scale geometric structures. We call our method salient edge and region aware image retargeting (SERAR). We evaluate our method visually, and compare the results with related methods. Our method performs well in retargeting images with cluttered backgrounds and in preserving large scale structures.     

Content- and disparity-adaptive stereoscopic image retargeting

The paper proposes a content- and disparity-adaptive stereoscopic image retargeting. To simultaneously avoid the saliency content and disparity distortion, firstly, we calculate the image saliency region distortion difference, and conclude the factors causing visual distortion. Then, the proposed method via a convex quadratic programming can simultaneously avoid the distortion of the salient region and adjust disparity to a target area, by considering the relationship of the scaling factor of salient region and the disparity scaling factor. The experimental results show that the proposed method is able to successfully adapt the image disparity to the target display screen, while the salient objects remain undistorted in the retargeted stereoscopic image.     

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.     

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...