【摘要】 单像素成像是一种仅需要使用无分辨能力的桶探测器结合空间光调制信息就能重构出一副完整图像的成像方式，具有非局域成像和高灵敏的特点，适合在外太空非合作目标下进行超远距离成像探测，但需要多次空间光调制后进行探测，重构图像信噪比低.本文提出一种基于全局注意力机制的低采样率下图像增强方法，利用Transformer结构搭建新型的SUNet(swin transformer unet)网络，解决传统卷积神经网络平移不变性和无法获得全局感受野的问题.根据切蛋糕(cake-cutting, CC)序改进的差分鬼成像算法在低采样条件下重构出低质量的图像，使用SUNet对图像进行增强.实验结果表明，该方法与2022年提出的GIDC(ghost imaging using deep neural network constraint)方法相比，在0.1的采样率下，峰值信噪比提升了3.29 dB,结构相似度提升了8%,为单像素成像的空间探测提供了新的技术途径.更多还原

【Abstract】 Single-pixel imaging is an imaging technique that reconstructs a complete image using only non-resolving bucket detectors combined with spatial light modulation information. It features non-local imaging and high sensitivity, making it suitable for ultra-long-distance imaging and detection of non-cooperative targets in outer space. However, it requires multiple spatial light modulations for detection, resulting in low signal-to-noise ratio in the reconstructed images. A global attention mechanism-based image enhancement method for low-sampling rates is presented in this paper. A novel SUNet(swin transformer unet)network is built via Transformer architecture to address the issues of translational invariance and limited global receptive field in traditional convolutional neural networks. Improved differential ghost imaging algorithm based on CC(cake-cutting)sequence is employed to reconstruct low-quality images under low sampling conditions, which are then enhanced by SUNet. Experimental results show that, compared to the GIDC(ghost imaging using deep neural network constraint)method proposed in 2022, this approach achieves 3.29 dB improvement in peak signal-to-noise ratio and 8% increase in structural similarity at 0.1 sampling rate, providing a new technological avenue for spatial detection in single-pixel imaging.更多还原