基于聚类稀疏表示与图像块自适应聚合的单幅图像超分辨研究

Single Image Super-Resolution by Clustered Sparse Representation and Adaptive Patch Aggregation

A Single Image Super-Resolution (SISR) reconstruction method that uses clustered sparse representation and adaptive patch aggregation is proposed. First, we randomly extract image patch pairs from the training images, and divide these patch pairs into dif-ferent groups by K-means clustering. Then, we learn an over-complete sub-dictionary pair offline from corresponding group patch pairs. For a given low-resolution patch, we adap-tively select one sub-dictionary to reconstruct the high resolution patch online. In addition, non-local self-similarity and steering kernel regression constraints are integrated into patch aggregation to improve the quality of the re-covered images. Experiments show that the proposed method is able to realize state-of-the-art performance in terms of both objective evaluation and visual perception.