EUVIMEDEUVIMED entdecken
Crossref

HoloSR: deep learning-based super-resolution for real-time high-resolution computer-generated holograms

Siwoo Lee, Seung-Woo Nam, Juhyun Lee, Yoonchan Jeong, Byoungho Lee

Optics Express · 25.03.2024 · 32 (7) · 11107

DOI: 10.1364/oe.516564 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Optics Express, online erschienen am 12.03.2024. Verfasst von Siwoo Lee und 4 weiteren Autor:innen. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 35 Literaturangaben. Gefördert von: Institute of Information & Communications Technology Planning & Evaluation grant funded by the Korean government.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study presents HoloSR, a novel deep learning-based super-resolution approach designed to produce high-resolution computer-generated holograms from low-resolution RGBD images, enabling the real-time production of realistic three-dimensional images. The HoloSR combines the enhanced deep super-resolution network with resize and convolution layers, facilitating the direct generation of high-resolution computer-generated holograms without requiring additional interpolation. Various upscaling scales, extending up to ×4, are evaluated to assess the performance of our method. Quantitative metrics such as structural similarity and peak signal-to-noise ratio are employed to measure the quality of the reconstructed images. Our simulation and experimental results demonstrate that HoloSR successfully achieves super-resolution by generating high-resolution holograms from low-resolution RGBD inputs with supervised and unsupervised learning.

Förderung

  • Institute of Information & Communications Technology Planning & Evaluation grant funded by the Korean government

Zitieren

APA

Lee, S., Nam, S. W., Lee, J., Jeong, Y., & Lee, B. (2024). HoloSR: deep learning-based super-resolution for real-time high-resolution computer-generated holograms. Optics Express, 32(7), 11107. https://doi.org/10.1364/oe.516564

Vancouver

Lee S, Nam SW, Lee J, Jeong Y, Lee B. HoloSR: deep learning-based super-resolution for real-time high-resolution computer-generated holograms. Optics Express. 2024;32(7):11107. doi:10.1364/oe.516564

BibTeX
@article{Lee2024,
  author = {Lee, Siwoo and Nam, Seung-Woo and Lee, Juhyun and Jeong, Yoonchan and Lee, Byoungho},
  title = {HoloSR: deep learning-based super-resolution for real-time high-resolution computer-generated holograms},
  journal = {Optics Express},
  year = {2024},
  volume = {32},
  number = {7},
  pages = {11107},
  doi = {10.1364/oe.516564}
}
Kostenlos starten →