一种基于稀疏表征的图像超分辨率重建方法

An image super-resolution method based on sparse representation

基于稀疏信号表征理论,同时利用稀疏约束和重建约束条件提出了一种对单幅图像超分辨率的方法.对于输入的低分辨率图像的每个图像块,寻找一种稀疏表征,然后用这些稀疏表征的系数来生成高分辨率输出图像.与以前单张图像重建的方法相比,该算法具有好的鲁棒性.

In this paper,based on the sparse signal representation theory,a method for single image super-resolution reconstruction using sparse constraint and constraint conditions is proposed.For each image block of the input low resolution image,the writers search for a sparse representation,and then use the coefficients of these sparse representation to generate high resolution output image.Compared with the previous methods,this algorithm has a good robustness.