Generative Bayesian Image Super Resolution With Natural Image Prior

Abstract

We propose a new single image super resolution (SR) algorithm via Bayesian modeling with a natural image prior modeled by a high-order Markov random field (MRF). SR is one of the long-standing and active topics in image processing community. It is of great use in many practical applications, such as astronomical observation, medical imaging, and the adaptation of low-resolution contents onto high-resolution displays. One category of the conventional approaches for image SR is formulating the problem with Bayesian modeling techniques and then obtaining its maximum-a-posteriori solution, which actually boils down to a regularized regression task. Although straightforward, this approach cannot exploit the full potential offered by the probabilistic modeling, as only the posterior mode is sought. On the other hand, current Bayesian SR approaches using the posterior mean estimation typically use very simple prior models for natural images to ensure the computational tractability. In this paper, we present a Bayesian image SR approach with a flexible high-order MRF model as the prior for natural images. The minimum mean square error (MMSE) criteria are used for estimating the HR image. A Markov chain Monte Carlo-based sampling algorithm is presented for obtaining the MMSE solution. The proposed method cannot only enjoy the benefits offered by the flexible prior, but also has the advantage of making use of the probabilistic modeling to perform a posterior mean estimation, thus is less sensitive to the local minima problem as the MAP solution. Experimental results indicate that the proposed method can generate competitive or better results than state-of-the-art SR algorithms.

Single Image Super Resolution : A Comparative Study

“…Second row shows the super resolution output from the method in [9]. The super resolution output from method in [23] is shown in third row. Fourth row introduces the super resolution output from method in [24].…”

“…Figure. 1 Examples of recovering super resolution images. Row 1 represents the original images, row 2 represents the results of method [9], row 3 represents the results of method [23], row 4 represents the results of method [24], and row 5 represents the results of method [17].…”

“…This guess can be obtained with the posterior mean, rather than the posterior mode [23] .To estimate the high resolution image, we take the advantage of sampling of high dimensional data for Gaussian Model and develop for MMSE for the HR image. In this method, Results compared with SR algorithms verify its effectiveness.…”

Sparse Dictionaries Learning for Fast Example-Based Super-Resolution

“…computer vision, medical image processing and remote sensing. Existing image SR researches can be divided into three main approaches: interpolation-based methods [1,2], reconstruction-based methods [3,4] and machine learning (ML) based methods [5,6]. The latter has been shown to achieve preferable results by using ML techniques.…”

Contour Model and Robust Segmentation based Human Pose Estimation in Images and Videos

“…Koray, who established a Cauchy distribution which based on the edge priori model [3], this model uses the dependency of pixel space maintain the clarity of the edges effectively, but such Cauchy scale parameter choosing still influence the edge distribution. Zhang et al who established the Laplacian prior model [4], extracting the edge of the image, but the TV priori cannot sufficiently captured image edge and may cause the piecewise linearity. Katsuki, who use a causal Gaussian MRF model as a priori knowledge [8], although this model considered the edge structure of the image, but it still cannot capture the statistical characteristics of natural images effectively.…”