Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
2 files | 4.63 MB
Add to list
  1. Search results
  2. Highly parallel steered mixture-of-ex...

Highly parallel steered mixture-of-experts rendering at pixel-level for image and light field data

Vasileios Avramelos, Ruben Verhack, Ignace Saenen (UGent) , Glenn Van Wallendael (UGent) , Bart Goossens (UGent) and Peter Lambert (UGent)
(2020) JOURNAL OF REAL-TIME IMAGE PROCESSING. 17(4). p.931-947
Author
Organization
Abstract
A novel image approximation framework called steered mixture-of-experts (SMoE) was recently presented. SMoE has multiple applications in coding, scale-conversion, and general processing of image modalities. In particular, it has strong potential for coding and streaming higher dimensional image modalities that are necessary to leverage full translational and rotational freedom (6 degrees-of-freedom) in virtual reality for camera captured images. In this paper, we analyze the rendering performance of SMoE for 2D images and 4D light fields. Two different GPU implementations that parallelize the SMoE regression step at pixel-level are presented, including experimental evaluations based on rendering performance and quality. In this paper it is shown that on appropriate hardware, an OpenCL implementation can achieve 85 fps and 22 fps for, respectively, 1080p and 4K renderings of large models with more than 100,000 of Gaussian kernels.
Keywords
Steered mixture-of-experts, Image compression, Light field rendering, Real-time rendering, GPU acceleration

Downloads

  • Download
    DS195 i.pdf
    • full text (Accepted manuscript)
    • |
    • open access
    • |
    • PDF
    • |
    • 2.73 MB
  • Download
    (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 1.90 MB

Citation

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

MLA
Avramelos, Vasileios, et al. “Highly Parallel Steered Mixture-of-Experts Rendering at Pixel-Level for Image and Light Field Data.” JOURNAL OF REAL-TIME IMAGE PROCESSING, vol. 17, no. 4, 2020, pp. 931–47, doi:10.1007/s11554-018-0843-3.
APA
Avramelos, V., Verhack, R., Saenen, I., Van Wallendael, G., Goossens, B., & Lambert, P. (2020). Highly parallel steered mixture-of-experts rendering at pixel-level for image and light field data. JOURNAL OF REAL-TIME IMAGE PROCESSING, 17(4), 931–947. https://doi.org/10.1007/s11554-018-0843-3
Chicago author-date
Avramelos, Vasileios, Ruben Verhack, Ignace Saenen, Glenn Van Wallendael, Bart Goossens, and Peter Lambert. 2020. “Highly Parallel Steered Mixture-of-Experts Rendering at Pixel-Level for Image and Light Field Data.” JOURNAL OF REAL-TIME IMAGE PROCESSING 17 (4): 931–47. https://doi.org/10.1007/s11554-018-0843-3.
Chicago author-date (all authors)
Avramelos, Vasileios, Ruben Verhack, Ignace Saenen, Glenn Van Wallendael, Bart Goossens, and Peter Lambert. 2020. “Highly Parallel Steered Mixture-of-Experts Rendering at Pixel-Level for Image and Light Field Data.” JOURNAL OF REAL-TIME IMAGE PROCESSING 17 (4): 931–947. doi:10.1007/s11554-018-0843-3.
Vancouver
1.
Avramelos V, Verhack R, Saenen I, Van Wallendael G, Goossens B, Lambert P. Highly parallel steered mixture-of-experts rendering at pixel-level for image and light field data. JOURNAL OF REAL-TIME IMAGE PROCESSING. 2020;17(4):931–47.
IEEE
[1]
V. Avramelos, R. Verhack, I. Saenen, G. Van Wallendael, B. Goossens, and P. Lambert, “Highly parallel steered mixture-of-experts rendering at pixel-level for image and light field data,” JOURNAL OF REAL-TIME IMAGE PROCESSING, vol. 17, no. 4, pp. 931–947, 2020.
@article{8670735,
  abstract     = {{A novel image approximation framework called steered mixture-of-experts (SMoE) was recently presented. SMoE has multiple applications in coding, scale-conversion, and general processing of image modalities. In particular, it has strong potential for coding and streaming higher dimensional image modalities that are necessary to leverage full translational and rotational freedom (6 degrees-of-freedom) in virtual reality for camera captured images. In this paper, we analyze the rendering performance of SMoE for 2D images and 4D light fields. Two different GPU implementations that parallelize the SMoE regression step at pixel-level are presented, including experimental evaluations based on rendering performance and quality. In this paper it is shown that on appropriate hardware, an OpenCL implementation can achieve 85 fps and 22 fps for, respectively, 1080p and 4K renderings of large models with more than 100,000 of Gaussian kernels.}},
  author       = {{Avramelos, Vasileios and Verhack, Ruben and Saenen, Ignace and Van Wallendael, Glenn and Goossens, Bart and Lambert, Peter}},
  issn         = {{1861-8200}},
  journal      = {{JOURNAL OF REAL-TIME IMAGE PROCESSING}},
  keywords     = {{Steered mixture-of-experts,Image compression,Light field rendering,Real-time rendering,GPU acceleration}},
  language     = {{eng}},
  number       = {{4}},
  pages        = {{931--947}},
  title        = {{Highly parallel steered mixture-of-experts rendering at pixel-level for image and light field data}},
  url          = {{http://dx.doi.org/10.1007/s11554-018-0843-3}},
  volume       = {{17}},
  year         = {{2020}},
}
Altmetric
View in Altmetric
Web of Science
Times cited: