Super Resolution of Images and Video

Katsaggelos, Aggelos K.; Molina, Rafael; Mateos, Javier

doi:10.2200/s00036ed1v01y200606ivm007

Cited by 87 publications

(78 citation statements)

References 107 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Although the super resolution literature is rich (see [1] for an extensive review) it is still an open and widely investigated topic. Recently, motivated by its success in image recovery problems, the use of the total variation (TV) function and its variants has become popular in super resolution.…”

Section: Introductionmentioning

confidence: 99%

Total variation super resolution using a variational approach

Babacan

Molina

Katsaggelos

2008

2008 15th IEEE International Conference on Image Processing

Self Cite

View full text Add to dashboard Cite

In this paper we propose a novel algorithm for super resolution based on total variation prior and variational distribution approximations. We formulate the problem using a hierarchical Bayesian model where the reconstructed high resolution image and the model parameters are estimated simultaneously from the low resolution observations. The algorithm resulting from this formulation utilizes variational inference and provides approximations to the posterior distributions of the latent variables. Due to the simultaneous parameter estimation, the algorithm is fully automated so parameter tuning is not required. Experimental results show that the proposed approach outperforms some of the state-of-the-art super resolution algorithms.

show abstract

Section: Introductionmentioning

confidence: 99%

Total variation super resolution using a variational approach

Babacan

Molina

Katsaggelos

2008

2008 15th IEEE International Conference on Image Processing

Self Cite

View full text Add to dashboard Cite

show abstract

“…The prior p(x) represents our a priori knowledge or expectation of the high-resolution image and it is often selected to be an MRF that imposes smoothness constraints on the image, reflecting our prior knowledge that neighboring pixels are likely to have similar values [2,4]. The prior can be understood as a regularizer of the superresolution problem, which is definitely ill-posed due to the downscale and irreversible noise processes.…”

Section: Mechanism Of Bayesian Superresolutionmentioning

confidence: 99%

“…Generally, matrices used in the prior have been selected as high-pass filters such as the difference filter, the Laplacian filter, or filters with wider spatial ranges [4]. The likelihood is defined according to our assumption of the observation process.…”

Section: Single-layer Bayesian Superresolutionmentioning

confidence: 99%

Bayesian image superresolution and hidden variable modeling

et al. 2010

View full text Add to dashboard Cite

Superresolution is an image processing technique that estimates an original high-resolution image from its low-resolution and degraded observations. In superresolution tasks, there have been problems regarding the computational cost for the estimation of high-dimensional variables. These problems are now being overcome by the recent development of fast computers and the development of powerful computational techniques such as variational Bayesian approximation. In this article, we review a Bayesian treatment of the superresolution problem and present its extensions based on hierarchical modeling by employing hidden variables.

show abstract

“…We use the term Super-Resolution (SR) to denote the process of obtaining an HR image, or a sequence of HR images, from a set of LR images [1]. Following the Bayesian framework we focus in this paper on the reconstruction of HR images from a set of downsampled, rotated, and shifted LR images, (see [1] and the references therein, [2] and [3]).…”

Section: Introductionmentioning

confidence: 99%

“…Following the Bayesian framework we focus in this paper on the reconstruction of HR images from a set of downsampled, rotated, and shifted LR images, (see [1] and the references therein, [2] and [3]). …”

Section: Introductionmentioning

confidence: 99%

Parameter Estimation in Bayesian Super-Resolution Image Reconstruction from Low Resolution Rotated and Translated Images

Villena

Vega

Molina

et al. 2009

Advanced Concepts for Intelligent Vision Systems

Self Cite

View full text Add to dashboard Cite

Abstract. This paper deals with the problem of high-resolution (HR) image reconstruction, from a set of degraded, under-sampled, shifted and rotated images, utilizing the variational approximation within the Bayesian paradigm. The proposed inference procedure requires the calculation of the covariance matrix of the HR image given the LR observations and the unknown hyperparameters of the probabilistic model. Unfortunately the size and complexity of such matrix renders its calculation impossible, and we propose and compare three alternative approximations. The estimated HR images are compared with images provided by other HR reconstruction methods.

show abstract

Super Resolution of Images and Video

Cited by 87 publications

References 107 publications

Total variation super resolution using a variational approach

Total variation super resolution using a variational approach

Bayesian image superresolution and hidden variable modeling

Parameter Estimation in Bayesian Super-Resolution Image Reconstruction from Low Resolution Rotated and Translated Images

Contact Info

Product

Resources

About