A Novel Video Super-Resolution Algorithm Based on Non-Local Normalized Convolution

At present, most of video super-resolution reconstruction algorithm make the reconstruction result blurred, especially around the edges. In order to solve this problem, we study the basic theory of normalized convolution (NC), which include the NC based on polynomial basis function and the least-square solution and propose a novel video sequence super-resolution reconstruction algorithm based on non-local normalized convolution in this chapter. This algorithm can be combined with gray-value information and structural details in the image. The density of sampled data and local structure in edge decide the shape and size of neighborhood in a pixel, so as to design certainty function and structural-adaptive applicability function. Experimental results prove that our proposed algorithm can provide improved denoising effect in the output image and achieve a state-of-art optical resolution in the image edges and detailed features.