Rizvi Saad, Cao Jie, Zhang Kaiyu, Hao Qun
Opt Express. 2020 Mar 2;28(5):7360-7374. doi: 10.1364/OE.385233.
Undersampling in Fourier single pixel imaging (FSI) is often employed to reduce imaging time for real-time applications. However, the undersampled reconstruction contains ringing artifacts (Gibbs phenomenon) that occur because the high-frequency target information is not recorded. Furthermore, by employing 3-step FSI strategy (reduced measurements with low noise suppression) with a low-grade sensor (i.e., photodiode), this ringing is coupled with noise to produce unwanted artifacts, lowering image quality. To improve the imaging quality of real-time FSI, a fast image reconstruction framework based on deep convolutional autoencoder network (DCAN) is proposed. The network through context learning over FSI artifacts is capable of deringing, denoising, and recovering details in 256 × 256 images. The promising experimental results show that the proposed deep-learning-based FSI outperforms conventional FSI in terms of image quality even at very low sampling rates (1-4%).
傅里叶单像素成像（FSI）中的欠采样通常用于减少实时应用的成像时间。然而，欠采样重建中会出现振铃伪影（吉布斯现象），这是由于高频目标信息未被记录而产生的。此外，通过采用三步FSI策略（减少测量次数并降低噪声抑制）和低等级传感器（即光电二极管），这种振铃会与噪声耦合，产生不需要的伪影，降低图像质量。为了提高实时FSI的成像质量，提出了一种基于深度卷积自动编码器网络（DCAN）的快速图像重建框架。该网络通过对FSI伪影进行上下文学习，能够对256×256图像进行去振铃、去噪和细节恢复。有前景的实验结果表明，即使在非常低的采样率（1-4%）下，所提出的基于深度学习的FSI在图像质量方面也优于传统FSI。
