Advanced search
1 file | 282.74 KB Add to list

Image Inpainting and demosaicing via total variation and Markov random field-based modeling

Author
Organization
Abstract
The problem of image reconstruction from incomplete data can be formulated as a linear inverse problem and is usually approached using optimization theory tools. Total variation (TV) regularization has been widely applied in this framework, due to its effectiveness in capturing spatial information and availability of elegant, fast algorithms. In this paper we show that significant improvements can be gained by extending this approach with a Markov Random Field (MRF) model for image gradient magnitudes. We propose a novel method that builds upon the Chambolle's fast projected algorithm designed for solving TV minimization problem. In the Chambolle's algorithm, we incorporate a MRF model which selects only a subset of image gradients to be effectively included in the algorithm iterations. The proposed algorithm is especially effective when a large portion of image data is missing. We also apply the proposed method to demosacking where algorithm shows less sensitivity to the initial choice of the tuning parameter and also for its wide range of values outperformes the method without the MRF model.
Keywords
inpainting, MRF, TV regularization

Downloads

  • (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 282.74 KB

Citation

Please use this url to cite or link to this publication:

MLA
Panic, Marko, et al. “Image Inpainting and Demosaicing via Total Variation and Markov Random Field-Based Modeling.” 2018 26TH TELECOMMUNICATIONS FORUM (TELFOR), 2018, pp. 301–04.
APA
Panic, M., Jakovetic, D., Crnojevic, V., & Pizurica, A. (2018). Image Inpainting and demosaicing via total variation and Markov random field-based modeling. In 2018 26TH TELECOMMUNICATIONS FORUM (TELFOR) (pp. 301–304). Belgrade, SERBIA.
Chicago author-date
Panic, Marko, Dusan Jakovetic, Vladimir Crnojevic, and Aleksandra Pizurica. 2018. “Image Inpainting and Demosaicing via Total Variation and Markov Random Field-Based Modeling.” In 2018 26TH TELECOMMUNICATIONS FORUM (TELFOR), 301–4.
Chicago author-date (all authors)
Panic, Marko, Dusan Jakovetic, Vladimir Crnojevic, and Aleksandra Pizurica. 2018. “Image Inpainting and Demosaicing via Total Variation and Markov Random Field-Based Modeling.” In 2018 26TH TELECOMMUNICATIONS FORUM (TELFOR), 301–304.
Vancouver
1.
Panic M, Jakovetic D, Crnojevic V, Pizurica A. Image Inpainting and demosaicing via total variation and Markov random field-based modeling. In: 2018 26TH TELECOMMUNICATIONS FORUM (TELFOR). 2018. p. 301–4.
IEEE
[1]
M. Panic, D. Jakovetic, V. Crnojevic, and A. Pizurica, “Image Inpainting and demosaicing via total variation and Markov random field-based modeling,” in 2018 26TH TELECOMMUNICATIONS FORUM (TELFOR), Belgrade, SERBIA, 2018, pp. 301–304.
@inproceedings{8631805,
  abstract     = {The problem of image reconstruction from incomplete data can be formulated as a linear inverse problem and is usually approached using optimization theory tools. Total variation (TV) regularization has been widely applied in this framework, due to its effectiveness in capturing spatial information and availability of elegant, fast algorithms. In this paper we show that significant improvements can be gained by extending this approach with a Markov Random Field (MRF) model for image gradient magnitudes. We propose a novel method that builds upon the Chambolle's fast projected algorithm designed for solving TV minimization problem. In the Chambolle's algorithm, we incorporate a MRF model which selects only a subset of image gradients to be effectively included in the algorithm iterations. The proposed algorithm is especially effective when a large portion of image data is missing. We also apply the proposed method to demosacking where algorithm shows less sensitivity to the initial choice of the tuning parameter and also for its wide range of values outperformes the method without the MRF model.},
  author       = {Panic, Marko and Jakovetic, Dusan and Crnojevic, Vladimir and Pizurica, Aleksandra},
  booktitle    = {2018 26TH TELECOMMUNICATIONS FORUM (TELFOR)},
  isbn         = {9781538671719},
  keywords     = {inpainting,MRF,TV regularization},
  language     = {eng},
  location     = {Belgrade, SERBIA},
  pages        = {301--304},
  title        = {Image Inpainting and demosaicing via total variation and Markov random field-based modeling},
  url          = {http://dx.doi.org/10.1109/telfor.2018.8612138},
  year         = {2018},
}

Altmetric
View in Altmetric
Web of Science
Times cited: