Multi-View Image Matting and Compositing Using Trimap Sharing for Natural 3-D Scene Generation
Multi-View Image Matting and Compositing Using Trimap Sharing for Natural 3-D Scene Generation
复制标题
DOI：
10.1109/3dtv.2008.4547892
复制
发表时间：
2008-05
期刊：
影响因子：
--
通讯作者：
Myung-Han Hyun;Sung-Yeol Kim;Yo-Sung Ho
中科院分区：
文献类型：
--
作者：
Myung-Han Hyun;Sung-Yeol Kim;Yo-Sung Ho
从图像中提取前景物体的数字抠图是电影业和广播中心产生特殊效果的重要过程。最近，已经开发了一种数字遮片算法，以使用从多视图图像生成的聚焦良好的图像来创建阿尔法遮片。然而，这种方法只能生成一个单视图阿尔法蒙版，即使它采用了多个相机。本文提出了一种通过共享参考视图的三重图来估计多视图Alpha遮罩的新方案。在我们从所有视图图像中提取前景对象之后，我们将前景对象与从相同的多视图相机布置捕获的相应背景图像合成。实验结果表明，多视点合成图像可以通过立体显示器生成合理自然的三维视图。
Digital matting for extracting foreground objects from an image is an important process to generate special effects in the movie industry and the broadcasting center. Recently, a digital matting algorithm has been developed to create an alpha matte using a well-focused image generated from multi-view images. However, this method could generate only a single-view alpha matte, even though it employed multiple cameras. In this paper, we propose a new estimation scheme for multi-view alpha mattes by sharing the trimap of the reference view. After we extract foreground objects from all view images, we composite the foreground objects with the corresponding background images captured from the same multi-view camera arrangement. Experimental results demonstrate that multi-view composite images can generate reasonably natural 3-D views through the stereoscopic monitor.