• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International conference on future information and communication engineering >Multi-View Stereoscopic Image Synthesis Algorithm for 3DTV
【24h】

Multi-View Stereoscopic Image Synthesis Algorithm for 3DTV

机译：3DTV的多视立体图像合成算法

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In this paper, we propose a multi-view stereoscopic image synthesis algorithm for 3DTV system using depth information with an RGB texture from a depth camera. The proposed algorithm synthesizes multi-view images which a virtual convergence camera model could generate. To furnish the motion parallax cue in each synthesized view, spatial and rotational transformation techniques were applied to foreground layer, and a new occlusion filling process was applied to both the foreground and background layers, as well. To add a stereoscopic depth cue to each synthesized view as a reference (left), we also generate a corresponding right view based on a virtual parallel camera model. Experimental results showed that the performance of the proposed algorithm is better than those of conventional methods.
机译：在本文中，我们提出了一种3DTV系统的多视图立体图像合成算法，该算法使用深度相机的RGB纹理的深度信息。所提出的算法合成了虚拟会聚相机模型可以生成的多视点图像。为了在每个合成视图中提供运动视差提示，将空间和旋转变换技术应用于前景层，并且还将新的遮挡填充过程应用于前景层和背景层。为了向每个合成视图添加立体深度提示作为参考（左），我们还基于虚拟并行相机模型生成了相应的右视图。实验结果表明，该算法的性能优于传统方法。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号