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

## TL;DR

DR2-Net is a deep residual network designed for fast and high-quality image reconstruction from compressive measurements, outperforming traditional and recent deep learning methods across various measurement rates.

## Contribution

The paper introduces DR2-Net, a novel deep residual reconstruction network that combines linear mapping and residual learning for improved image reconstruction from compressive sensing data.

## Key findings

- DR2-Net outperforms traditional iterative algorithms.
- DR2-Net surpasses recent deep learning-based methods.
- Significant quality improvements at multiple measurement rates.

## Abstract

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 \textbf{D}eep \textbf{R}esidual \textbf{R}econstruction Network (DR$^{2}$-Net) to reconstruct the image from its Compressively Sensed (CS) measurement. The DR$^{2}$-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, DR$^{2}$-Net consists of two components, \emph{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 DR$^{2}$-Net by adding several residual learning blocks to enhance the preliminary image. Extensive experiments demonstrate that the DR$^{2}$-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 DR$^{2}$-Net has been released on: https://github.com/coldrainyht/caffe\_dr2