Most deep learning-based compressed sensing (DCS) algorithms adopt a single neural network for signal reconstruction and fail to jointly consider the influences of the sampling operation for reconstruction. In this paper, we propose a unified framework, which jointly considers the sampling and reconstruction process for image compressive sensing based on well-designed cascade neural networks. Two sub-networks, which are the sampling sub-network and the reconstruction sub-network, are included in the proposed framework. In the sampling sub-network, an adaptive fully connected layer instead of the traditional random matrix is used to mimic the sampling operator. In the reconstruction sub-network, a cascade network combining stacked denoising autoencoder (SDA) and convolutional neural network (CNN) is designed to reconstruct signals. The SDA is used to solve the signal mapping problem, and the signals are initially reconstructed. Furthermore, CNN is used to fully recover the structure and texture features of the image to obtain better reconstruction performance. Extensive experiments show that this framework outperforms many other state-of-the-art methods, especially at low sampling rates.

大多数基于深度学习的压缩感知（DCS）算法采用单个神经网络进行信号重构，未能共同考虑采样操作对重构的影响。在本文中，我们提出了一个统一的框架，该框架基于精心设计的级联神经网络，共同考虑图像压缩感知的采样和重建过程。所提出的框架中包含两个子网络，即采样子网络和重建子网络。在采样子网络中，使用自适应全连接层代替传统的随机矩阵来模拟采样算子。在重建子网络中，设计了一个结合堆叠去噪自编码器（SDA）和卷积神经网络（CNN）的级联网络来重建信号。SDA用于解决信号映射问题，对信号进行初步重构。此外，CNN用于完全恢复图像的结构和纹理特征以获得更好的重建性能。大量实验表明，该框架优于许多其他最先进的方法，尤其是在低采样率下。