Image super-resolution by dictionary concatenation and sparse representation with approximate L0 norm minimization

This paper proposes a different image super-resolution (SR) reconstruction scheme, based on the newly advanced results of sparse representation and the recently presented SR methods via this model. Firstly, we online learn a subsidiary dictionary with the degradation estimation of the given low-resolution image, and concatenate it with main one offline learned from many natural images with high quality. This strategy can strengthen the expressive ability of dictionary atoms. Secondly, the conventional matching pursuit algorithms commonly use a fixed sparsity threshold for sparse decomposition of all image patches, which is not optimal and even introduces annoying artifacts. Alternatively, we employ the approximate L0 norm minimization to decompose accurately the patch over its dictionary. Thus the coefficients of representation with variant number of nonzero items can exactly weight atoms for those complicated local structures of image. Experimental results show that the proposed method produces high-resolution images that are competitive or superior in quality to results generated by similar techniques.

Figure optionsDownload as PowerPoint slideHighlights
► Universal dictionary and fixed sparsity are not beneficial to super-resolution.
► We use dictionary concatenation and more precise sparse representation algorithm.
► Universal dictionary is cascaded with specific one learned from given image.
► Approximate L0 norm minimization overcomes disadvantage of fixed sparsity.
► Various reconstruction results show effectiveness of proposed framework.