IEEE Trans Image Process. 2015 Nov;24(11):3624-36. doi: 10.1109/TIP.2015.2447836. Epub 2015 Jun 19.
In this paper, we address the problem of recovering degraded images using multivariate Gaussian mixture model (GMM) as a prior. The GMM framework in our method for image restoration is based on the assumption that the accumulation of similar patches in a neighborhood are derived from a multivariate Gaussian probability distribution with a specific covariance and mean. Previous methods of image restoration with GMM have not considered spatial (geometric) distance between patches in clustering. Our conducted experiments show that in the case of constraining Gaussian estimates into a finite-sized windows, the patch clusters are more likely to be derived from the estimated multivariate Gaussian distributions, i.e., the proposed statistical patch-based model provides a better goodness-of-fit to statistical properties of natural images. A novel approach for computing aggregation weights for image reconstruction from recovered patches is introduced which is based on similarity degree of each patch to the estimated Gaussian clusters. The results admit that in the case of image denoising, our method is highly comparable with the state-of-the-art methods, and our image interpolation method outperforms previous state-of-the-art methods.
在本文中，我们通过多元高斯混合模型（GMM）作为先验来解决退化图像的恢复问题。我们的图像恢复方法中的 GMM 框架基于这样的假设，即来自特定协方差和均值的多元高斯概率分布的相似块的积累。之前使用 GMM 进行图像恢复的方法没有考虑到聚类中块之间的空间（几何）距离。我们的实验表明，在将高斯估计约束到有限大小的窗口中的情况下，块聚类更有可能来自估计的多元高斯分布，即，所提出的基于统计块的模型提供了对自然图像统计特性的更好的拟合度。提出了一种新颖的方法来计算从恢复的块进行图像重建的聚合权重，该方法基于每个块与估计的高斯聚类的相似程度。结果表明，在图像去噪的情况下，我们的方法与最先进的方法高度可比，并且我们的图像插值方法优于以前的最先进方法。
