Automatic superresolution image reconstruction based on hybrid MAP-POCS

Image superresolution (SR) reconstruction refers to methods that increase image spatial resolution by fusing information from either a sequence of temporal adjacent images or multi-source images from different sensors. In the paper we propose a hybrid MAP-POCS method for automatic image SR reconstruction, which firstly estimates the unknown point spread function (PSF) and an approximation for the original ideal image, and then sets up the HMRF image prior model and assesses its inhomogeneous control parameter through maximum likelihood (ML) estimation, finally automatically computes the regularized solution by two-phase iterative solution. Hybrid MAP-POCS estimates computed on simulation images, actual video sequence and actual satellite images show dramatic visual and quantitative improvements over bilinear interpolation and ML-POCS reconstruction results with sharp edges, correctly restored textures and a high PSNR improvement.