Advanced search
2 files | 2.19 MB Add to list

Progressive modeling of steered mixture-of-experts for light field video approximation

Author
Organization
Abstract
Steered Mixture-of-Experts (SMoE) is a novel framework for the approximation, coding, and description of image modalities. The future goal is to arrive at a representation for Six Degrees-of-Freedom (6DoF) image data. The goal of this paper is to introduce SMoE for 4D light field videos by including the temporal dimension. However, these videos contain vast amounts of samples due to the large number of views per frame. Previous work on static light field images mitigated the problem by hard subdividing the modeling problem. However, such a hard subdivision introduces visually disturbing block artifacts on moving objects in dynamic image data. We propose a novel modeling method that does not result in block artifacts while minimizing the computational complexity and which allows for a varying spread of kernels in the spatio-temporal domain. Experiments validate that we can progressively model light field videos with increasing objective quality up to 0.97 SSIM.

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 1.47 MB
  • DS167 i.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 718.41 KB

Citation

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

MLA
Verhack, Ruben, et al. “Progressive Modeling of Steered Mixture-of-Experts for Light Field Video Approximation.” 2018 PICTURE CODING SYMPOSIUM (PCS 2018), IEEE, 2018, pp. 268–72.
APA
Verhack, R., Van Wallendael, G., Courteaux, M., Lambert, P., & Sikora, T. (2018). Progressive modeling of steered mixture-of-experts for light field video approximation. In 2018 PICTURE CODING SYMPOSIUM (PCS 2018) (pp. 268–272). San Francisco, CA, USA: IEEE.
Chicago author-date
Verhack, Ruben, Glenn Van Wallendael, Martijn Courteaux, Peter Lambert, and Thomas Sikora. 2018. “Progressive Modeling of Steered Mixture-of-Experts for Light Field Video Approximation.” In 2018 PICTURE CODING SYMPOSIUM (PCS 2018), 268–72. IEEE.
Chicago author-date (all authors)
Verhack, Ruben, Glenn Van Wallendael, Martijn Courteaux, Peter Lambert, and Thomas Sikora. 2018. “Progressive Modeling of Steered Mixture-of-Experts for Light Field Video Approximation.” In 2018 PICTURE CODING SYMPOSIUM (PCS 2018), 268–272. IEEE.
Vancouver
1.
Verhack R, Van Wallendael G, Courteaux M, Lambert P, Sikora T. Progressive modeling of steered mixture-of-experts for light field video approximation. In: 2018 PICTURE CODING SYMPOSIUM (PCS 2018). IEEE; 2018. p. 268–72.
IEEE
[1]
R. Verhack, G. Van Wallendael, M. Courteaux, P. Lambert, and T. Sikora, “Progressive modeling of steered mixture-of-experts for light field video approximation,” in 2018 PICTURE CODING SYMPOSIUM (PCS 2018), San Francisco, CA, USA, 2018, pp. 268–272.
@inproceedings{8578315,
  abstract     = {Steered Mixture-of-Experts (SMoE) is a novel framework for the approximation, coding, and description of image modalities. The future goal is to arrive at a representation for Six Degrees-of-Freedom (6DoF) image data. The goal of this paper is to introduce SMoE for 4D light field videos by including the temporal dimension. However, these videos contain vast amounts of samples due to the large number of views per frame. Previous work on static light field images mitigated the problem by hard subdividing the modeling problem. However, such a hard subdivision introduces visually disturbing block artifacts on moving objects in dynamic image data. We propose a novel modeling method that does not result in block artifacts while minimizing the computational complexity and which allows for a varying spread of kernels in the spatio-temporal domain. Experiments validate that we can progressively model light field videos with increasing objective quality up to 0.97 SSIM.},
  author       = {Verhack, Ruben and Van Wallendael, Glenn and Courteaux, Martijn and Lambert, Peter and Sikora, Thomas},
  booktitle    = {2018 PICTURE CODING SYMPOSIUM (PCS 2018)},
  isbn         = {9781538641606},
  language     = {eng},
  location     = {San Francisco, CA, USA},
  pages        = {268--272},
  publisher    = {IEEE},
  title        = {Progressive modeling of steered mixture-of-experts for light field video approximation},
  url          = {http://dx.doi.org/10.1109/pcs.2018.8456242},
  year         = {2018},
}

Altmetric
View in Altmetric
Web of Science
Times cited: