Image Super-Resolution via Sparse Bayesian Modeling of Natural Images

TL;DR

This paper introduces a Bayesian super-resolution method that models natural images with sparse, content-adaptive priors, leading to faster and more accurate high-resolution image reconstruction.

Contribution

It presents a novel Empirical Bayesian approach with latent variables in a high-order MRF, capturing correlations and improving over traditional MAP-based methods.

Findings

Achieves competitive or superior super-resolution results

Faster estimation compared to MCMC-based methods

Models correlations in sparse coefficients effectively

Abstract

Image super-resolution (SR) is one of the long-standing and active topics in image processing community. A large body of works for image super resolution formulate the problem with Bayesian modeling techniques and then obtain its Maximum-A-Posteriori (MAP) solution, which actually boils down to a regularized regression task over separable regularization term. Although straightforward, this approach cannot exploit the full potential offered by the probabilistic modeling, as only the posterior mode is sought. Also, the separable property of the regularization term can not capture any correlations between the sparse coefficients, which sacrifices much on its modeling accuracy. We propose a Bayesian image SR algorithm via sparse modeling of natural images. The sparsity property of the latent high resolution image is exploited by introducing latent variables into the high-order Markov Random Field (MRF) which capture the content adaptive variance by pixel-wise adaptation. The high-resolution image is estimated via Empirical Bayesian estimation scheme, which is substantially faster than our previous approach based on Markov Chain Monte Carlo sampling [1]. It is shown that the actual cost function for the proposed approach actually incorporates a non-factorial regularization term over the sparse coefficients. Experimental results indicate that the proposed method can generate competitive or better results than \emph{state-of-the-art} SR algorithms.