EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Generating Multi‐Depth 3D Holograms Using a Fully Convolutional Neural Network

Xingpeng Yan iD, Xinlei Liu iD, Jiaqi Li, Yanan Zhang, Hebin Chang, Tao Jing, Hairong Hu, Qiang Qu, Xi Wang, Xiaoyu Jiang

Advanced Science · 2024-07 · 11 (28)

DOI: 10.1002/advs.202308886 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Science, online erschienen am 09.05.2024. Verfasst von Xingpeng Yan und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Information Communication, Army Academy of Armored Forces, Beijing, 100072, China. Die Arbeit wurde bisher 34-mal zitiert (Crossref) und nennt 76 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Efficiently generating 3D holograms is one of the most challenging research topics in the field of holography. This work introduces a method for generating multi‐depth phase‐only holograms using a fully convolutional neural network (FCN). The method primarily involves a forward–backward‐diffraction framework to compute multi‐depth diffraction fields, along with a layer‐by‐layer replacement method (L 2 RM) to handle occlusion relationships. The diffraction fields computed by the former are fed into the carefully designed FCN, which leverages its powerful non‐linear fitting capability to generate multi‐depth holograms of 3D scenes. The latter can smooth the boundaries of different layers in scene reconstruction by complementing information of occluded objects, thus enhancing the reconstruction quality of holograms. The proposed method can generate a multi‐depth 3D hologram with a PSNR of 31.8 dB in just 90 ms for a resolution of 2160 × 3840 on the NVIDIA Tesla A100 40G tensor core GPU. Additionally, numerical and experimental results indicate that the generated holograms accurately reconstruct clear 3D scenes with correct occlusion relationships and provide excellent depth focusing.

Schlagwörter

Stichwörter der Autor:innen

computer‐generated hologramfully convolutional neural networkmulti‐depth hologram

Autor:innen und Institutionen

  • Department of Information Communication, Army Academy of Armored Forces, Beijing, 100072, China.
  • National Digital Switching System Engineering and Technological Research Center, Zhengzhou, 450001, China.
  • Information Engineering University, Zhengzhou, 450001, China.

ORCID-Profile: Xingpeng Yan, Xinlei Liu

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Yan, X., Liu, X., Li, J., Zhang, Y., Chang, H., Jing, T., Hu, H., Qu, Q., Wang, X., & Jiang, X. (2024). Generating Multi‐Depth 3D Holograms Using a Fully Convolutional Neural Network. Advanced Science, 11(28). https://doi.org/10.1002/advs.202308886

Vancouver

Yan X, Liu X, Li J, Zhang Y, Chang H, Jing T, et al. Generating Multi‐Depth 3D Holograms Using a Fully Convolutional Neural Network. Advanced Science. 2024;11(28). doi:10.1002/advs.202308886

BibTeX
@article{Yan2024,
  author = {Yan, Xingpeng and Liu, Xinlei and Li, Jiaqi and Zhang, Yanan and Chang, Hebin and Jing, Tao and Hu, Hairong and Qu, Qiang and Wang, Xi and Jiang, Xiaoyu},
  title = {Generating Multi‐Depth 3D Holograms Using a Fully Convolutional Neural Network},
  journal = {Advanced Science},
  year = {2024},
  volume = {11},
  number = {28},
  doi = {10.1002/advs.202308886}
}
Kostenlos starten →