Image reconstruction from random samples with parametric and nonparametric modeling

Statistical image modeling is essential for many image processing tasks that are ill-posed in nature. Existing image models can be categorized as parametric models and nonparametric models according to the statistical techniques used. In this paper, we develop a new image reconstruction algorithm from sparse random samples based on hybrid parametric and non- parametric modeling of images. More specifically, the modeling strength of the parametric and nonparametric techniques are combined within a multiscale framework where the parametric and nonparametric image models are used to solve the interscale and intrascale estimation problems, respectively. The proposed algorithm is capable of recovering the image from very sparse samples (e.g. 5%), and experimental results suggest the proposed algorithm achieves significant improvement over existing pure parametric and nonparametric based approaches both in terms of PSNR and subjective qualities of the reconstruction results.