Advanced search
2 files | 4.76 MB Add to list

Hard real-time, pixel-parallel rendering of light field videos using steered mixture-of-experts

Ignace Saenen (UGent) , Ruben Verhack (UGent) , Vasileios Avramelos (UGent) , Glenn Van Wallendael (UGent) and Peter Lambert (UGent)
Author
Organization
Abstract
Steered Mixture-of-Experts (SMoE) is a novel framework for the approximation, coding, and description of image modalities such as light field images and video. The future goal is to arrive at a representation for Six Degrees-of-Freedom (6DoF) image data. Previous research has shown the feasibility of real-time pixel-parallel rendering of static light field images. Each pixel is independently reconstructed by kernels that lay in its vicinity. The number of kernels involved forms the bottleneck on the achievable framerate. The goal of this paper is twofold. Firstly, we introduce pixel-level rendering of light field video, as previous work only rendered static content. Secondly, we investigate rendering using a predefined number of most significant kernels. As such, we can deliver hard real-time constraints by trading off the reconstruction quality.

Downloads

  • (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 3.19 MB
  • DS168 i.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 1.57 MB

Citation

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

MLA
Saenen, Ignace, et al. “Hard Real-Time, Pixel-Parallel Rendering of Light Field Videos Using Steered Mixture-of-Experts.” 2018 PICTURE CODING SYMPOSIUM (PCS 2018), IEEE, 2018, pp. 337–41.
APA
Saenen, I., Verhack, R., Avramelos, V., Van Wallendael, G., & Lambert, P. (2018). Hard real-time, pixel-parallel rendering of light field videos using steered mixture-of-experts. In 2018 PICTURE CODING SYMPOSIUM (PCS 2018) (pp. 337–341). San Francisco, CA, USA: IEEE.
Chicago author-date
Saenen, Ignace, Ruben Verhack, Vasileios Avramelos, Glenn Van Wallendael, and Peter Lambert. 2018. “Hard Real-Time, Pixel-Parallel Rendering of Light Field Videos Using Steered Mixture-of-Experts.” In 2018 PICTURE CODING SYMPOSIUM (PCS 2018), 337–41. IEEE.
Chicago author-date (all authors)
Saenen, Ignace, Ruben Verhack, Vasileios Avramelos, Glenn Van Wallendael, and Peter Lambert. 2018. “Hard Real-Time, Pixel-Parallel Rendering of Light Field Videos Using Steered Mixture-of-Experts.” In 2018 PICTURE CODING SYMPOSIUM (PCS 2018), 337–341. IEEE.
Vancouver
1.
Saenen I, Verhack R, Avramelos V, Van Wallendael G, Lambert P. Hard real-time, pixel-parallel rendering of light field videos using steered mixture-of-experts. In: 2018 PICTURE CODING SYMPOSIUM (PCS 2018). IEEE; 2018. p. 337–41.
IEEE
[1]
I. Saenen, R. Verhack, V. Avramelos, G. Van Wallendael, and P. Lambert, “Hard real-time, pixel-parallel rendering of light field videos using steered mixture-of-experts,” in 2018 PICTURE CODING SYMPOSIUM (PCS 2018), San Francisco, CA, USA, 2018, pp. 337–341.
@inproceedings{8578312,
  abstract     = {Steered Mixture-of-Experts (SMoE) is a novel framework for the approximation, coding, and description of image modalities such as light field images and video. The future goal is to arrive at a representation for Six Degrees-of-Freedom (6DoF) image data. Previous research has shown the feasibility of real-time pixel-parallel rendering of static light field images. Each pixel is independently reconstructed by kernels that lay in its vicinity. The number of kernels involved forms the bottleneck on the achievable framerate. The goal of this paper is twofold. Firstly, we introduce pixel-level rendering of light field video, as previous work only rendered static content. Secondly, we investigate rendering using a predefined number of most significant kernels. As such, we can deliver hard real-time constraints by trading off the reconstruction quality.},
  author       = {Saenen, Ignace and Verhack, Ruben and Avramelos, Vasileios and Van Wallendael, Glenn and Lambert, Peter},
  booktitle    = {2018 PICTURE CODING SYMPOSIUM (PCS 2018)},
  isbn         = {9781538641606},
  language     = {eng},
  location     = {San Francisco, CA, USA},
  pages        = {337--341},
  publisher    = {IEEE},
  title        = {Hard real-time, pixel-parallel rendering of light field videos using steered mixture-of-experts},
  url          = {http://dx.doi.org/10.1109/PCS.2018.8456306},
  year         = {2018},
}

Altmetric
View in Altmetric
Web of Science
Times cited: