Advanced search
1 file | 405.91 KB Add to list

RGB-NIR demosaicing using deep residual U-Net

Ivana Shopovska (UGent) , Ljubomir Jovanov (UGent) and Wilfried Philips (UGent)
Author
Organization
Abstract
Multi-spectral image acquisition brings numerous potential benefits in computer vision and image processing applications. Single-sensor acquisition helps to overcome problems with misalignments occurring in multiple-sensor acquisition. However, the single-sensor approach poses the problem of interpolation of missing values. In this paper we propose an adapted version of a residual U-Net, with application in demosaicing. The experiments show that the proposed method achieves state-of-the-art results, and has good generalization capabilities to different color filter array patterns.
Keywords
CFA, CNN, deep learning, demosaicing, RGB-NIR, single-sensor, U-Net

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 405.91 KB

Citation

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

MLA
Shopovska, Ivana, et al. “RGB-NIR Demosaicing Using Deep Residual U-Net.” 2018 26TH TELECOMMUNICATIONS FORUM (TELFOR), IEEE, 2018, pp. 297–300.
APA
Shopovska, I., Jovanov, L., & Philips, W. (2018). RGB-NIR demosaicing using deep residual U-Net. In 2018 26TH TELECOMMUNICATIONS FORUM (TELFOR) (pp. 297–300). Belgrade, Serbia: IEEE.
Chicago author-date
Shopovska, Ivana, Ljubomir Jovanov, and Wilfried Philips. 2018. “RGB-NIR Demosaicing Using Deep Residual U-Net.” In 2018 26TH TELECOMMUNICATIONS FORUM (TELFOR), 297–300. IEEE.
Chicago author-date (all authors)
Shopovska, Ivana, Ljubomir Jovanov, and Wilfried Philips. 2018. “RGB-NIR Demosaicing Using Deep Residual U-Net.” In 2018 26TH TELECOMMUNICATIONS FORUM (TELFOR), 297–300. IEEE.
Vancouver
1.
Shopovska I, Jovanov L, Philips W. RGB-NIR demosaicing using deep residual U-Net. In: 2018 26TH TELECOMMUNICATIONS FORUM (TELFOR). IEEE; 2018. p. 297–300.
IEEE
[1]
I. Shopovska, L. Jovanov, and W. Philips, “RGB-NIR demosaicing using deep residual U-Net,” in 2018 26TH TELECOMMUNICATIONS FORUM (TELFOR), Belgrade, Serbia, 2018, pp. 297–300.
@inproceedings{8591644,
  abstract     = {Multi-spectral image acquisition brings numerous potential benefits in computer vision and image processing applications. Single-sensor acquisition helps to overcome problems with misalignments occurring in multiple-sensor acquisition. However, the single-sensor approach poses the problem of interpolation of missing values. In this paper we propose an adapted version of a residual U-Net, with application in demosaicing. The experiments show that the proposed method achieves state-of-the-art results, and has good generalization capabilities to different color filter array patterns.},
  articleno    = {18395084},
  author       = {Shopovska, Ivana and Jovanov, Ljubomir and Philips, Wilfried},
  booktitle    = {2018 26TH TELECOMMUNICATIONS FORUM (TELFOR)},
  isbn         = {9781538671719},
  keywords     = {CFA,CNN,deep learning,demosaicing,RGB-NIR,single-sensor,U-Net},
  language     = {eng},
  location     = {Belgrade, Serbia},
  pages        = {18395084:297--18395084:300},
  publisher    = {IEEE},
  title        = {RGB-NIR demosaicing using deep residual U-Net},
  url          = {http://dx.doi.org/10.1109/TELFOR.2018.8611819},
  year         = {2018},
}

Altmetric
View in Altmetric
Web of Science
Times cited: