基于改进BP算法的中间视合成方法

本文提出了一种新颖的基于改进BP算法的中间视合成方法。方法中首先改进了BP(Belief Propagation)算法来提高视差估计的正确率,然后在视图插值中设计了新的插值策略,在区域分类的基础上有针对地进行中间视合成。实验结果表明,采用本文提出的中间视合成方法可以获得具有很好视觉效果的虚拟视图。      

基于视差场校正和区域分割的中间视图像生成与内插方法

针对中间视图像生成依赖于精确稠密视差场估计以及遮挡区域检测的问题,提出了利用被编码传输的视差场进行中间视生成与内插算法,避免了复杂的视差场估计。本文算法将区域分割与视差场校正相结合,可对原有的误匹配视差进行校正。在中间视内插中,使用区域分割技术来对具有遮挡和模糊区域的内容进行判断,最后根据视差场的特性进行填充。实验结果表明生成的中间视图像具有良好的视觉效果。     

交互式立体显示中基于图像拼合的视点合成

在立体显示中,视点合成是实现交互性的关键技术,即在三维(3D)场景中通过自由选择视点而获得环视能力.本文将视点插值和基于图像拼合的视点变形技术相结合,提出一种中间视合成算法.首先均匀化原始立体图像对;然后只对前景对象区域进行视差估计以提高视差匹配的速度和精度;接着确定左右视点中的可靠区域,根据可靠区域生成过渡中间视点;最后,采用视点插值结合变形的方法,由过渡视合成中间视点.实验结果表明合成的中间视点图像质量良好,而且合成速度也明显提高.本文算法可用于实时 3D 视频应用的交互式立体显示,可以实现任意视点的实时绘制.     

基于冗余小波变换的立体图像视差估计

通过分析目前立体视差估计方法的不足,提出一种基于冗余小波变换的视差估计新算法.首先对参考图像进行冗余小波变换,提取特征点,形成DT(Delaunay Triangle)网格,然后根据三角形特征点在目标图像中进行视差估计,最后通过仿射变换形成浓密视差图.实验表明该算法能有效获得视差矢量,视差匹配后能得到良好的重建图像.     

一种基于立体视邻接帧时空相关性的最小代价函数帧估计算法

为了在立体视频序列编码中获得高的压缩率,需要对立体视频序列中一个视的序列按传统方法进行独立编码;另一个视的序列中,只对其中一些参考帧(I帧或P帧)按视差补偿预测的方法进行编码,其余帧不进行编码和传输,而在解码端用立体视帧估计的方法得到重建.本文提出了一种基于立体视中邻接帧在图像、视差场和运动矢量场之间高度相关性的方法.对于因遮挡而缺乏估计的区域,则结合了图像强度的连续性和运动,视差矢量的分布特性,构造了代价方程并估计出该部分的运动矢量及强度值.实验证明,重建出来的帧图像在视觉和信噪比意义上均具有较好的效果.     

基于均值漂移的立体视频对象分割

提出了一种结合深度信息与改进的均值漂移算法相结合的立体视频对象分割方法.首先采用自适应权值的视差估计方法.获得可靠的视差图,然后利用改进的均值漂移算法对视差图进行分割,获取视频对象.实验结果表明,该方法可以获得与语义一致的对象分割.     

基于Mean Shift立体匹配的视图合成算法及仿真

立体匹配一直是计算机视觉和图像处理领域的中心研究问题。文中提出一种基于Mean Shift算法理论的区域分割图像的立体匹配方法,实现水平方向任意位置的视图合成。新的立体匹配方法是根据分割区域像素间的颜色相似性和多窗口的权值匹配代价函数实现立体图像的匹配,通过上述匹配法得到的视差图采用winner-take-all进行优化视差值并对其做平滑操作,最后采用正向视图插值方法对任意位置进行视图合成。实验结果表明,该算法具有良好的图像分割效果,较小的视图误差,轮廓清晰,具有良好的立体效果。     

调整量最小的多视图像校正算法

在多视自由视点电视（FTV）系统中,摄像机阵列拍摄的多视视频存在垂直视差、且水平视差分布不均等问题,严重影响合成视频的质量效果。现有的多视图像校正方法虽然消除了垂直视差,但是校正图像过程中引入的旋转和平移失真较大,使人眼产生不舒适感。为此,本文提出一种适于平行摄像机阵列的多视图像校正算法,首先建立理想的摄像机安放位置,然后计算多视图像校正变换,将实拍图像映射到理想摄像机位置处,得到校正后图像。在设计理想的摄像机安放位置时,考虑人眼视觉特性,确保坐标轴旋转和平移调整量最小化,实现多视图像校正变换引入图像失真总量最小。实验表明,该算法不仅可以消除垂直视差,而且图像校正过程中引入的失真小,符合人眼视觉习惯,能有效改善合成视的图像质量,提高人眼观看舒适程度。      

零视差点重组在三维图像数字水印中的应用

在基于深度图像渲染（DIBR）水印方案中,利用深度图像和中央彩色图像通过像素平移渲染出左眼视图和右眼视图,嵌入到中央图像的水印信息会受到严重破坏,无法在左眼视图和右眼视图中正确提取水印信息。本文提出一种DIBR中零视差点的三维图像数字水印方法,利用深度值确定视差值,标定视差为零的点,重新组合成新的载体图像,进行水印嵌入。由于视差为零的像素点在生成左右眼视图时没有发生水平移动,所以此方法克服了DIBR过程中的像素平移带来的攻击。实验证明此方法能得到和二维水印一致的效果并且对于高斯噪声和JPEG压缩都具有良好的鲁棒性。      

基于图像的中间视合成方法综述

中间视合成是多视点显示中的一种关键技术,广泛应用于三维电视和三维远程视频会议系统中.分析了中间视合成方法的研究现状,讨论了基于图像插值的中间视合成中存在的问题,展望了进一步研究的方向.     

极端学习四元数小波特征的立体图像质量评价

为了有效、实时地对各种类型失真立体图像质量 进行评价,提出了一种基于极端学习(ELM) 和四元数小波交换(QWT)的无参考(NR)立体图像质量评价方法。首先利用SSI M密度立体匹 配模型生成相关的视差图、差异度可信图和右视图差异补偿图3D映射图;然后分别对左右视 图、视差图和差异度可信图进行 QWT,计算图像QWT第3相位系数相位幅值加权标准差和能量;再计算右视图 差异补偿图统 计特征熵和中值;最后将所提取的所有特征输入到基于核映射ELM 学习,预测失真立体图像 质量。在LIVE 3D图像质量评价数据库上的实验结果表明,本方法与人类主观质量评分具有较好的一致性 。在LIVE 3D图 像质量库I(Phase I)和库II(Phase II)上的斯皮尔曼相关系数(SROCC) 分别达到0.926和0.914     

Edge-preserving disparity estimation and disparity-compensated intermediate view reconstruction for stereo images

A constrained disparity estimation method is proposed which uses a directional regularization technique to efficiently preserve edges for stereo image coding. The proposed method smoothes disparity vectors in smooth regions and preserves edges in object boundaries well, without creating an oversmoothing problem. The differential pulse code modulation (DPCM) technique for disparity map coding is used prior to entropy coding, in order to improve the overall coding efficiency. The proposed disparity estimation method can also be applied to intermediate view reconstruction. Intermediate views between a left image and a right image provide reality and natural motion parallax to multiviewers. Intermediate views are synthesized by appropriately exploiting an interpolation or an extrapolation technique according to the characteristics of each region after identifying the regions as occluded regions, normal regions, and regions having ambiguous disparities.The experimental results show that the proposed disparity estimation method gives close matches between a left image and a right image and improves coding efficiency. In addition, we can subjectively confirm that the application of our proposed intermediate view reconstruction method leads to satisfactory intermediate views from a stereo image pair.This work was supported by the Korea Institute of Science and Technology (KIST) under Grant No. 99HI-054.     

Stereo image analysis for multi-viewpoint telepresence applications

An improved method for combined motion and disparity estimation in stereo sequences to synthesize temporally and perspectively intermediate views is presented. The main problems of matching methods for motion and disparity analysis are summarised. The improved concept is based on a modified block matching algorithm in which a cost function consisting of feature- and area-based correlation together with an appropriately weighted temporal smoothness term is applied. Considerable improvements have been obtained with respect to the motion and disparity assignments by introducing a confidence measure to evaluate the reliability of estimated correspondences. In occluded image areas, enhanced results are obtained applying an edge-assisted vector interpolation strategy. Two different image synthesis concepts are presented. The first concept is suitable for processing natural stereo sequences. It comprises the detection of covered and uncovered image areas caused by motion or disparity. This information is used to switch between different interpolation and extrapolation modes during the computation of intermediate views. The proposed object-based approach is suitable for processing typical video conference scenes containing extremely large occluded image regions and keeping implementation costs low. A set of stereo sequences has been processed. The performed computer simulations show that a continuous motion parallax can be obtained with good image quality by using sequences taken with stereo cameras having large interaxial distances.     

Bayesian winner-take-all reconstruction of intermediate views fromstereoscopic images

This paper presents a new algorithm for the reconstruction of intermediate views from a pair of still stereoscopic images. The algorithm is designed to address the issue of blur caused by linear filtering often employed in such reconstruction. The proposed algorithm is block-based and to reconstruct the intermediate views employs nonlinear disparity-compensated filtering by means of a winner-take-all strategy. The reconstructed image is modeled as a tiling by fixed-size blocks coming from various positions (disparity compensation) of either the left or right images, while the tiling map itself is modeled by a binary decision field. In addition to that, an observation model relating the left and right images via a disparity field, and a disparity field model are used. All models are probabilistic and are combined into a maximum a posteriori probability criterion. The intermediate intensities, disparities and the binary decision field are estimated jointly using the expectation-maximization algorithm. The new approach is compared experimentally on complex natural images with a reference block-based algorithm employing linear filtering. Although the improvements are localized and often subtle, they demonstrate that a high-quality intermediate view reconstruction for complex scenes is feasible.     

Virtual Control of Optical Axis of the 3DTV Camera for Reducing Visual Fatigue in Stereoscopic 3DTV

In stereoscopic television, there is a trade‐off between visual comfort and 3‐dimensional (3D) impact with respect to the baseline‐stretch of a 3DTV camera. It is necessary to adjust the baseline‐stretch at an appropriate distance depending on the contents of a scene if we want to obtain a subjectively optimal quality of an image. However, it is very hard to obtain a small baseline‐stretch using commercially available cameras of broadcasting quality where the sizes of the lens and CCD module are large. In order to overcome this limitation, we attempt to freely control the baseline‐stretch of a stereoscopic camera by synthesizing the virtual views at the desired location of interval between two cameras. This proposed technique is based on the stereo matching and view synthesis techniques. We first obtain a dense disparity map using a hierarchical stereo matching with the edge‐adaptive multiple shifted windows. Then, we synthesize the virtual views using the disparity map. Simulation results with various stereoscopic images demonstrate the effectiveness of the proposed technique.     

Quality Enhancement for Hybrid 3DTV with Mixed Resolution Using Conditional Replenishment Algorithm

This paper proposes a conditional replenishment algorithm (CRA) to improve the visual quality (where spatial resolutions of the left and right views are mismatched) of a hybrid stereoscopic 3DTV that is based on the ATSC‐M/H standard. So as to generate an enhanced view, the CRA is to choose the better substitute among a disparity‐compensated view with high quality and a simply interpolated view. The CRA generates a disparity map that includes modes and disparity vectors as additional information. It also employs a quad‐tree structure with variable block size by considering the spatial correlation of disparity vectors. In addition, it takes advantage of the disparity map used in a previous frame to keep the amount of additional information as small as possible. The simulation results show that the proposed CRA can successfully improve the peak signal‐to‐noise ratio of a poor‐quality view and consequently have a positive effect on the subjective quality of the resulting 3D view.     

多分辨率与视差梯度相结合的快速区域匹配

针对传统区域匹配算法中存在大量冗余计算,提出了一种多分辨率与视差梯度相结合的快速匹配算法。首先通过均值采样得到低分辨率图像对,再通过改进的视差梯度约束算法进行匹配得到低分辨率图像的视差图,最后引入盒滤波思想指导原始视差图的生成。实验表明,该快速匹配算法相对于传统的区域匹配算法,在改善精度的同时,减少了三倍以上运算时间。     

基于稀疏-密集匹配算法的视差度量

图像匹配是一种约束最优化问题，系统是否收敛于全局最优值一直尚未解决。为得到密集连续的视差图，通常在匹配算法中引入唯一性、连续性、有序性约束。但对于遮挡区域的像素，其对应点并不存在，因此过度平滑的视差结果会导致在遮挡边缘处，灰度变化显著的表面渗透至邻接的灰度变化和缓的表面，出现所谓的表面膨胀缩小现象。当定义图像匹配算法中最优匹配标准时，必须根据图像的内在信息加入其他一些约束条件，保证遮挡存在下匹配结果的全局精确度。提出一种稀疏-密集的匹配算法，利用能量图确定稀疏的视差图，然后运用相位匹配方法对视差图进行内插，并结合最优化理论克服局部最优困扰。实现遮挡检测。立体像对的匹配试验结果表明了该方法的有效性。     

基于未匹配子带合成系数统计特性的立体图像质量评价算法

针对经典立体图像质量评价算法存在评价准确性 低以及特征提取耗时较长的问题, 提出一种基于未匹配子带合成系数统计特性的立体图像质量评价算法。首先,利用可控金字 塔对左右视点图像进行多尺度、多方向的小波分解,并将左右视点图像在相同尺度、相同方 向上未经视差图匹配的小波子带系数合成为子带合成系数。其次,提取小波子带合成系数中 的统计分布特征,相同尺度相邻方向小波子带合成系数之间的相关性特征,以及相同方向相 邻尺度子带合成系数之间的相关性特征。最后,利用所提取特征训练经典的支持向量回归模 型,预测图像质量。在LIVE 3D和Waterloo IVC 3D数据库上的实验结果表明,与主流立体 图像质量评价算法相比,本文算法在预测对称和非对称失真立体图像质量时都获得了更高的 评价准确性。同时,由于子带合成系数的生成无需根据视差图进行匹配,算法执行效率高。     

A mesh-based disparity representation method for view interpolation and stereo image compression.

This paper proposes a mesh-based representation method for the disparity map of stereo images. The proposed method is designed to concentrate mainly on applications of view interpolation and stereo image compression. To obtain high image quality in the view interpolation and compression of stereo images, we formulate the view-interpolation error and prediction error. In the formulation, the view-interpolation and prediction errors depend not only on the accuracy of the disparity map, but also on the gradient of the stereo images. The proposed representation method for the disparity map is based on a triangular mesh structure, which minimizes the formulated interpolation and prediction errors. The experimental results show that the proposed method yields higher quality view-interpolated images and also has better performance in stereo image compression than the conventional methods.