Abstract

In this paper, an end-to-end depth neural network based on a conditional generative adversarial network for computational ghost imaging (CGANCGI) is proposed to restore clear object images with high quality at a sub-Nyquist sampling rate. The 2D light signal collected by a CMOS camera and the gray image of the original measured object are used as the input of the network model; then, the CGANCGI network is trained, and the measured object image is recovered directly from the 2D light signal. Experiments have verified that the proposed method only needs 1/10 of traditional deep learning samples to achieve fast image restoration with high-quality, and its peak signal-to-noise ratio and structural similarity are, respectively, four to six times and five to seven times higher than those of the original image, which prove that our method has practical application prospects in ghost imaging under low sampling rates.

© 2022 Optica Publishing Group

High-speed computational ghost imaging based on an auto-encoder network under low sampling rate

Wei Feng, Xingyu Sun, Xiuhua Li, Junhui Gao, Xiaodong Zhao, and Daxing Zhao
Appl. Opt. 60(16) 4591-4598 (2021)

Color computational ghost imaging by deep learning based on simulation data training

Zhan Yu, Yang Liu, Jinxi Li, Xing Bai, Zhongzhuo Yang, Yang Ni, and Xin Zhou
Appl. Opt. 61(4) 1022-1029 (2022)

Ghost translation: an end-to-end ghost imaging approach based on the transformer network

Wenhan Ren, Xiaoyu Nie, Tao Peng, and Marlan O. Scully
Opt. Express 30(26) 47921-47932 (2022)

End-to-end computational ghost imaging method that suppresses atmospheric turbulence

Leihong Zhang, Yunjie Zhai, Runchu Xu, Kaimin Wang, and Dawei Zhang
Appl. Opt. 62(3) 697-705 (2023)

Low sampling high quality image reconstruction and segmentation based on array network ghost imaging

Xuan Liu, Tailin Han, Cheng Zhou, Jipeng Huang, Mingchi Ju, Bo Xu, and Lijun Song
Opt. Express 31(6) 9945-9960 (2023)