Single image super resolution utilizing a graph based restoration model

Speaker: Cory Falconer (MCSC)

Abstract: Given we live in a digital age where images are regularly being viewed, posted, or utilized, spectators of such images on occasion could prefer a higher resolution perspective. The process of producing a high-resolution image given a single low-resolution noisy measurement is called single-frame image super resolution (SISR). Many interpolation schemes fail to preserve important edge information of images and cannot be used blindly for resolution enhancement.
In general, a-priori constraints can be imposed on the high resolution image approximation. This process is called regularization. We model our SISR problem as an energy minimization procedure which optimally balances data fidelity and the regularization term. The goal of this work is to analyze the effectiveness of incorporating a series of data-adaptive graph Laplacian filters to our data fidelity term. The regularization will incorporate natural image redundancy implicitly via the so called normalized graph Laplacian operator. Finally, a conjugate gradient scheme is used to minimize the objective functional. Promising results on resolution enhancement of digital images will be presented.