一种面向视点绘制的深度图像后处理方法-计算机工程与应用.PDF

158 2015 ，51（11） Computer Engineering and Applications 计算机工程与应用 一种面向视点绘制的深度图像后处理方法 潘云峰，李福翠，邵 枫 PAN Yunfeng, LI Fucui, SHAO Feng 宁波大学 信息与工程学院，浙江 宁波 315211 School of Information Science and Engineering, Ningbo University, Ningbo, Zhejiang 315211, China PAN Yunfeng, LI Fucui, SHAO Feng. Depth map post-processing method for view synthesis. Computer Engineering and Applications, 2015, 51 （11）：158-161. Abstract ：Depth image based rendering is one of the key technologies in three-dimensional system. However, coding distortion in depth map will affect the following performance of virtual view synthesis. In this paper, a depth map post-processing method is proposed for virtual view synthesis. In the method, the filtering window size for each pixel is established based on the intersection of confidence intervals rule. The depth value for each pixel within the filtering window is estimated by using least square polynomial approximation. A weighted mode filtering is applied to the estimated depth map, and the filtered depth map is obtained. Experimental results show that, the proposed method can accurately recover the depth information from the decoded depth map, and promote the performance of virtual view synthesis. Key words ：depth map post-processing; intersection of confidence intervals; least square polynomial approximation; weighted mode filtering 摘 要：基于深度图像的绘制是三维视频系统中的一项关键技术。然而，深度编码失真会对后续虚拟视点绘制的性 能产生极大的影响。提出了一种面向虚拟视点绘制的深度图像后处理方法，利用基于置信区间的交点规则确定深 度图像中每个像素点的滤波窗口，利用最小均方逼近多项式技术估计每个像素点的深度值，再利用加权模式滤波器 对估计的深度图像进行滤波处理，得到深度滤波图像。实验结果表明，该方法能够精确地恢复出真实深度信息，提 高虚拟视点图像的绘制性能。 关键词：深度图像后处理；置信区间的交点；最小均方逼近多项式技术；加权模式滤波器 文献标志码：A 中图分类号：TN911.73 doi ：10.3778/j.issn. 1002-8331.1306-0383 1 引言 已提出了一些深度预处理技术。Zhang 等采用非对称 [3] 3DTV （Three Dimensional Television ）系统通常采