Opt Lett. 2023 Apr 15;48(8):2066-2069. doi: 10.1364/OL.480190.
Generally, the imaging quality of Fourier single-pixel imaging (FSI) will severely degrade while achieving high-speed imaging at a low sampling rate (SR). To tackle this problem, a new, to the best of our knowledge, imaging technique is proposed: firstly, the Hessian-based norm constraint is introduced to deal with the staircase effect caused by the low SR and total variation regularization; secondly, based on the local similarity prior of consecutive frames in the time dimension, we designed the temporal local image low-rank constraint for the FSI, and combined the spatiotemporal random sampling method, the redundancy image information of consecutive frames can be utilized sufficiently; finally, by introducing additional variables to decompose the optimization problem into multiple sub-problems and analytically solving each one, a closed-form algorithm is derived for efficient image reconstruction. Experimental results show that the proposed method improves imaging quality significantly compared with state-of-the-art methods.
通常情况下，在低采样率（SR）下实现高速成像时，傅里叶单像素成像（FSI）的成像质量会严重下降。针对这一问题，提出了一种新的、据我们所知的成像技术：首先，引入基于Hessian 的范数约束来处理低 SR 和全变差正则化引起的阶梯效应；其次，基于时间维度上连续帧的局部相似性先验，我们为 FSI 设计了时间局部图像低秩约束，并且结合时空随机采样方法，可以充分利用连续帧的冗余图像信息；最后，通过引入额外变量将优化问题分解为多个子问题，并对每个子问题进行解析求解，推导出了一种用于高效图像重建的闭式算法。实验结果表明，与现有方法相比，所提出的方法显著提高了成像质量。
