一种用于遮挡目标的W形自监督计算鬼成像恢复方法。

A W-Shaped Self-Supervised Computational Ghost Imaging Restoration Method for Occluded Targets.

作者信息

Wang Yu, Wang Xiaoqian, Gao Chao, Yu Zhuo, Wang Hong, Zhao Huan, Yao Zhihai

机构信息

Department of Physics, Changchun University of Science and Technology, Changchun 130022, China.

School of Physics and Electronics, Baicheng Normal University, Baicheng 137000, China.

出版信息

Sensors (Basel). 2024 Jun 28;24(13):4197. doi: 10.3390/s24134197.

DOI:10.3390/s24134197

PMID:39000976

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11244037/

Abstract

We developed a novel method based on self-supervised learning to improve the ghost imaging of occluded objects. In particular, we introduced a W-shaped neural network to preprocess the input image and enhance the overall quality and efficiency of the reconstruction method. We verified the superiority of our W-shaped self-supervised computational ghost imaging (WSCGI) method through numerical simulations and experimental validations. Our results underscore the potential of self-supervised learning in advancing ghost imaging.

摘要

我们开发了一种基于自监督学习的新方法，以改进被遮挡物体的鬼成像。具体而言，我们引入了一个W形神经网络来预处理输入图像，并提高重建方法的整体质量和效率。我们通过数值模拟和实验验证，证实了我们的W形自监督计算鬼成像（WSCGI）方法的优越性。我们的结果强调了自监督学习在推动鬼成像方面的潜力。