Single Image Super-Resolution With Non-Local Means and Steering Kernel Regression
Single Image Super-Resolution With Non-Local Means and Steering Kernel Regression
复制标题
DOI：
10.1109/tip.2012.2208977
复制
发表时间：
2012-11
影响因子：
10.6
通讯作者：
Kaibing Zhang;Xinbo Gao;D. Tao;Xuelong Li
中科院分区：
文献类型：
--
作者：
Kaibing Zhang;Xinbo Gao;D. Tao;Xuelong Li
图像超分辨率重构本质上是一个不适定问题，因此设计有效的先验算法非常重要。为此，我们提出了一种新的图像SR方法，通过从给定的低分辨率图像中学习非局部和局部正则化先验。非局部先验利用了自然图像中相似块的冗余性，而局部先验假设目标像素可以通过其相邻像素的加权平均来估计。基于以上考虑，我们利用非局部均值过滤器学习非局部先验，利用转向核回归学习局部先验。通过组合两个互补的正则化项，我们提出了SR恢复的最大后验概率框架。实验结果表明，该方法可以在定量和感知上重构出更高质量的结果。
Image super-resolution (SR) reconstruction is essentially an ill-posed problem, so it is important to design an effective prior. For this purpose, we propose a novel image SR method by learning both non-local and local regularization priors from a given low-resolution image. The non-local prior takes advantage of the redundancy of similar patches in natural images, while the local prior assumes that a target pixel can be estimated by a weighted average of its neighbors. Based on the above considerations, we utilize the non-local means filter to learn a non-local prior and the steering kernel regression to learn a local prior. By assembling the two complementary regularization terms, we propose a maximum a posteriori probability framework for SR recovery. Thorough experimental results suggest that the proposed SR method can reconstruct higher quality results both quantitatively and perceptually.