论文标题
快速，噪声单像素成像的深度学习正交基础模式
Deep-learned orthogonal basis patterns for fast, noise-robust single-pixel imaging
论文作者
论文摘要
单像素成像（SPI）是一种新颖的，非常规的方法，它超出了传统相机的概念，但对于实时应用来说，计算量昂贵且缓慢。已经提出了深度学习作为解决SPI重建问题的替代方法，但是在使用SPI时，对其性能和生成的基础模式进行了详细分析是有限的。我们在64x64像素图像上为SPI提供了一个改良的深卷积自动编码器网络（DCAN），其压缩率高达6.25％，并在训练过程中应用了二进制和正交的正规化器。使用这些正规化器训练DCAN可以学习具有二元或非二进制组合以及正交或非正交模式的多个测量库。我们将模式的重建质量，正交性和鲁棒性与所得DCAN模型的噪声与传统的SPI重建算法（例如总变化最小化和傅立叶变换）进行了比较。我们的DCAN模型可以接受训练，以使噪声具有稳健性，同时仍然具有足够快的重建时间（每帧〜3 ms），可为实时成像可行。
Single-pixel imaging (SPI) is a novel, unconventional method that goes beyond the notion of traditional cameras but can be computationally expensive and slow for real-time applications. Deep learning has been proposed as an alternative approach for solving the SPI reconstruction problem, but a detailed analysis of its performance and generated basis patterns when used for SPI is limited. We present a modified deep convolutional autoencoder network (DCAN) for SPI on 64x64 pixel images with up to 6.25% compression ratio and apply binary and orthogonality regularizers during training. Training a DCAN with these regularizers allows it to learn multiple measurement bases that have combinations of binary or non-binary, and orthogonal or non-orthogonal patterns. We compare the reconstruction quality, orthogonality of the patterns, and robustness to noise of the resulting DCAN models to traditional SPI reconstruction algorithms (such as Total Variation minimization and Fourier Transform). Our DCAN models can be trained to be robust to noise while still having fast enough reconstruction times (~3 ms per frame) to be viable for real-time imaging.
