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

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 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/caffe_dr2 .

[1]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[2]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[3]  Li Ma,et al.  Probabilistic class structure regularized sparse representation graph for semi-supervised hyperspectral image classification , 2017, Pattern Recognit..

[4]  Richard G. Baraniuk,et al.  From Denoising to Compressed Sensing , 2014, IEEE Transactions on Information Theory.

[5]  Pavan K. Turaga,et al.  ReconNet: Non-Iterative Reconstruction of Images from Compressively Sensed Measurements , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Mike E. Davies,et al.  Iterative Hard Thresholding for Compressed Sensing , 2008, ArXiv.

[7]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[8]  Rob Fergus,et al.  Depth Map Prediction from a Single Image using a Multi-Scale Deep Network , 2014, NIPS.

[9]  Aggelos K. Katsaggelos,et al.  DeepBinaryMask: Learning a Binary Mask for Video Compressive Sensing , 2016, Digit. Signal Process..

[10]  J. Tropp,et al.  CoSaMP , 2010, Commun. ACM.

[11]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Pavel Zemcík,et al.  Compression Artifacts Removal Using Convolutional Neural Networks , 2016, J. WSCG.

[14]  Andrea Montanari,et al.  Message-passing algorithms for compressed sensing , 2009, Proceedings of the National Academy of Sciences.

[15]  Volkan Cevher,et al.  Model-Based Compressive Sensing , 2008, IEEE Transactions on Information Theory.

[16]  Guangming Shi,et al.  Compressive Sensing via Nonlocal Low-Rank Regularization , 2014, IEEE Transactions on Image Processing.

[17]  Xiaoming Yuan,et al.  Alternating algorithms for total variation image reconstruction from random projections , 2012 .

[18]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[19]  I. Daubechies,et al.  An iterative thresholding algorithm for linear inverse problems with a sparsity constraint , 2003, math/0307152.

[20]  Guillermo Sapiro,et al.  Non-local sparse models for image restoration , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[21]  Richard G. Baraniuk,et al.  A deep learning approach to structured signal recovery , 2015, 2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[22]  Li Ma,et al.  Spatial and class structure regularized sparse representation graph for semi-supervised hyperspectral image classification , 2018, Pattern Recognit..

[23]  Yonina C. Eldar,et al.  Block-Sparse Signals: Uncertainty Relations and Efficient Recovery , 2009, IEEE Transactions on Signal Processing.

[24]  Stéphane Mallat,et al.  Matching pursuits with time-frequency dictionaries , 1993, IEEE Trans. Signal Process..

[25]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Xiaoou Tang,et al.  Learning a Deep Convolutional Network for Image Super-Resolution , 2014, ECCV.

[27]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[28]  Thomas S. Huang,et al.  Image Super-Resolution Via Sparse Representation , 2010, IEEE Transactions on Image Processing.

[29]  Alessandro Foi,et al.  Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering , 2007, IEEE Transactions on Image Processing.

[30]  Pavan K. Turaga,et al.  ReconNet: Non-Iterative Reconstruction of Images from Compressively Sensed Random Measurements , 2016, ArXiv.

[31]  Shuicheng Yan,et al.  Image Classification With Tailored Fine-Grained Dictionaries , 2018, IEEE Transactions on Circuits and Systems for Video Technology.

[32]  Yin Zhang,et al.  An efficient augmented Lagrangian method with applications to total variation minimization , 2013, Computational Optimization and Applications.

[33]  Lei Zhang,et al.  Image reconstruction with locally adaptive sparsity and nonlocal robust regularization , 2012, Signal Process. Image Commun..

[34]  Aggelos K. Katsaggelos,et al.  Deep fully-connected networks for video compressive sensing , 2016, Digit. Signal Process..

[35]  Joel A. Tropp,et al.  Signal Recovery From Random Measurements Via Orthogonal Matching Pursuit , 2007, IEEE Transactions on Information Theory.

[36]  Enhong Chen,et al.  Image Denoising and Inpainting with Deep Neural Networks , 2012, NIPS.

[37]  Piotr Indyk,et al.  A fast approximation algorithm for tree-sparse recovery , 2014, 2014 IEEE International Symposium on Information Theory.