An Application of Matting Laplacian Matrix to Range Image Super-Resolution

摘要：

This paper describes a successful application of Matting Laplacian Matrix to the problem of generating highresolution range images. The Matting Laplacian Matrix in this paper exploits the fact that discontinuities in range and coloring tend to co-align, which enables us to generate highresolution range image by integrating regular camera image into the range date. Using one registered and potentially highresolution camera image as reference, we iteratively refine the input low-resolution range image, in terms of both its spatial resolution and depth precision. We show that by using such a Matting Laplacian Matrix, we can get high-quality highresolution range images.

关键词： Range Measuring Technology Range Image Super-Resolution Matting Laplacian Matrix Steepest Descent Method

作者: Yuxiang Yang Zengfu Wang

作者单位: University of Science and Technology of China Joint Laboratory of Intelligent Science and Technology University of Science and Technology of China Joint Laboratory of Intelligent Science and Technology

会议类型: 国内会议

会议名称: 2011中国人工生命与智能机器人会议

会议地点: 合肥

会议语种:英文

页码: 1-4

在线出版日期: 2011-10-15（万方平台首次上网日期，不代表论文的发表时间）