Patch-based image Super Resolution using generalized Gaussian mixture model

TL;DR

This paper introduces a patch-based super resolution algorithm that learns a generalized Gaussian mixture model from low and high resolution patch pairs, improving image quality through MMSE reconstruction.

Contribution

It proposes a novel method to learn a joint GGMM from patch pairs for enhanced super resolution, advancing existing patch-based approaches.

Findings

The MMSE-GGMM method performs competitively with state-of-the-art techniques.

Numerical evaluations demonstrate improved image reconstruction quality.

The approach effectively models patch distributions for super resolution.

Abstract

Single Image Super Resolution (SISR) methods aim to recover the clean images in high resolution from low resolution observations.A family of patch-based approaches have received considerable attention and development. The minimum mean square error (MMSE) methodis a powerful image restoration method that uses a probability model on the patches of images. This paper proposes an algorithm to learn a jointgeneralized Gaussian mixture model (GGMM) from a pair of the low resolution patches and the corresponding high resolution patches fromthe reference data. We then reconstruct the high resolution image based on the MMSE method. Our numerical evaluations indicate that theMMSE-GGMM method competes with other state of the art methods.