DR2-Net: Deep Residual Reconstruction Network for Image Compressive Sensing

Most traditional algorithms for compressive sensing image reconstruction suffer from the intensive computation. Recently, deep learning-based reconstruction algorithms have been reported, which dramatically reduce the time complexity than iterative reconstruction algorithms. In this paper, we propose a novel Deep Residual Reconstruction Network (DR2-Net) to reconstruct the image from its Compressively Sensed (CS) measurement. The DR2-Net is proposed based on two observations: 1) linear mapping could reconstruct a high-quality preliminary image, and 2) residual learning could further improve the reconstruction quality. Accordingly, DR2-Net consists of two components, i.e., linear mapping network and residual network, respectively. Specifically, the fully-connected layer in neural network implements the linear mapping network. We then expand the linear mapping network to DR2-Net by adding several residual learning blocks to enhance the preliminary image. Extensive experiments demonstrate that the DR2-Net outperforms traditional iterative methods and recent deep learning-based methods by large margins at measurement rates 0.01, 0.04, 0.1, and 0.25, respectively. The code of DR2-Net has been released on: https://github.com/coldrainyht/caffedr2