Soft Edge Smoothness Prior for Alpha Channel Super Resolution
Soft Edge Smoothness Prior for Alpha Channel Super Resolution
复制标题
DOI：
10.1109/cvpr.2007.383028
复制
发表时间：
2007-06
期刊：
影响因子：
--
通讯作者：
Shengyang Dai;Mei Han;W. Xu;Ying Wu;Yihong Gong
中科院分区：
文献类型：
--
作者：
Shengyang Dai;Mei Han;W. Xu;Ying Wu;Yihong Gong
由于图像的严重欠定性，有效的图像先验是实现图像超分辨率的必要条件。虽然边缘平滑度先验可以是有效的，但是通常难以具有分析形式来评估边缘平滑度，特别是对于表现出逐渐强度过渡的软边缘。本文通过推广Geocuts方法（Y。Boykov和V.Kolmogorov，2003年），并证明了软边缘平滑度的措施近似的平均长度的所有水平线的强度图像。这一新的发现不仅导致了软边缘平滑先验的解析表征，而且给出了直观的几何解释。通过这种新形式的先验对超分辨率问题进行正则化，可以同时最小化所有水平线的长度，从而产生视觉上吸引人的结果。此外，本文还提出了一种新的结合这种软边缘平滑先验和alpha抠图技术的彩色图像超分辨率，通过归一化边缘片段与他们的alpha通道描述，以实现统一的处理不同的对比度和规模的边缘。
Effective image prior is necessary for image super resolution, due to its severely under-determined nature. Although the edge smoothness prior can be effective, it is generally difficult to have analytical forms to evaluate the edge smoothness, especially for soft edges that exhibit gradual intensity transitions. This paper finds the connection between the soft edge smoothness and a soft cut metric on an image grid by generalizing the Geocuts method (Y. Boykov and V. Kolmogorov, 2003), and proves that the soft edge smoothness measure approximates the average length of all level lines in an intensity image. This new finding not only leads to an analytical characterization of the soft edge smoothness prior, but also gives an intuitive geometric explanation. Regularizing the super resolution problem by this new form of prior can simultaneously minimize the length of all level lines, and thus resulting in visually appealing results. In addition, this paper presents a novel combination of this soft edge smoothness prior and the alpha matting technique for color image super resolution, by normalizing edge segments with their alpha channel description, to achieve a unified treatment of edges with different contrast and scale.