A Bayesian Nonparametric Approach to Image Super-resolution

TL;DR

This paper introduces a Bayesian nonparametric model for image super-resolution that learns visual patterns from data, using an efficient online variational Bayes algorithm for large-scale applications.

Contribution

It develops a novel Bayesian nonparametric approach employing a beta-Bernoulli process and introduces an online VB algorithm for scalable super-resolution.

Findings

The model effectively learns visual patterns from data.

The online VB algorithm is faster and scalable.

Results outperform several existing models.

Abstract

Super-resolution methods form high-resolution images from low-resolution images. In this paper, we develop a new Bayesian nonparametric model for super-resolution. Our method uses a beta-Bernoulli process to learn a set of recurring visual patterns, called dictionary elements, from the data. Because it is nonparametric, the number of elements found is also determined from the data. We test the results on both benchmark and natural images, comparing with several other models from the research literature. We perform large-scale human evaluation experiments to assess the visual quality of the results. In a first implementation, we use Gibbs sampling to approximate the posterior. However, this algorithm is not feasible for large-scale data. To circumvent this, we then develop an online variational Bayes (VB) algorithm. This algorithm finds high quality dictionaries in a fraction of the time needed by the Gibbs sampler.