Multi-input mutual supervision network for single-pixel computational imaging
Optics Express · 08.04.2024 · 32 (8) · 13224
DOI: 10.1364/oe.510683 ↗Kurz gefasst
Fachartikel in der Zeitschrift Optics Express, online erschienen am 26.03.2024. Verfasst von Zhipeng Geng und 6 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 22 Literaturangaben. Gefördert von: National Key Research and Development Program of China, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
In this study, we propose a single-pixel computational imaging method based on a multi-input mutual supervision network (MIMSN). We input one-dimensional (1D) light intensity signals and two-dimensional (2D) random image signal into MIMSN, enabling the network to learn the correlation between the two signals and achieve information complementarity. The 2D signal provides spatial information to the reconstruction process, reducing the uncertainty of the reconstructed image. The mutual supervision of the reconstruction results for these two signals brings the reconstruction objective closer to the ground truth image. The 2D images generated by the MIMSN can be used as inputs for subsequent iterations, continuously merging prior information to ensure high-quality imaging at low sampling rates. The reconstruction network does not require pretraining, and 1D signals collected by a single-pixel detector serve as labels for the network, enabling high-quality image reconstruction in unfamiliar environments. Especially in scattering environments, it holds significant potential for applications.
Förderung
- National Key Research and Development Program of China
- Fundamental Research Funds for the Central Universities
Zitieren
APA
Geng, Z., Sun, Z., Chen, Y., Lu, X., Tian, T., Cheng, G., & Li, X. (2024). Multi-input mutual supervision network for single-pixel computational imaging. Optics Express, 32(8), 13224. https://doi.org/10.1364/oe.510683
Vancouver
Geng Z, Sun Z, Chen Y, Lu X, Tian T, Cheng G, et al. Multi-input mutual supervision network for single-pixel computational imaging. Optics Express. 2024;32(8):13224. doi:10.1364/oe.510683
BibTeX
@article{Geng2024,
author = {Geng, Zhipeng and Sun, Zhe and Chen, Yifan and Lu, Xin and Tian, Tong and Cheng, Guanghua and Li, Xuelong},
title = {Multi-input mutual supervision network for single-pixel computational imaging},
journal = {Optics Express},
year = {2024},
volume = {32},
number = {8},
pages = {13224},
doi = {10.1364/oe.510683}
}
EUVIMED