Adaptive Measurement Network for CS Image Reconstruction

Conventional compressive sensing (CS) reconstruction is very slow for its characteristic of solving an optimization problem. Convolutional neural network can realize fast processing while achieving comparable results. While CS image recovery with high quality not only depends on good reconstruction algorithms, but also good measurements. In this paper, we propose an adaptive measurement network in which measurement is obtained by learning. The new network consists of a fully-connected layer and ReconNet. The fully-connected layer which has low-dimension output acts as measurement. We train the fully-connected layer and ReconNet simultaneously and obtain adaptive measurement. Because the adaptive measurement fits dataset better, in contrast with random Gaussian measurement matrix, under the same measurement rate, it can extract the information of scene more efficiently and get better reconstruction results. Experiments show that the new network outperforms the original one.

[1]  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).

[2]  Ali Bilgin,et al.  Compressed sensing using a Gaussian Scale Mixtures model in wavelet domain , 2010, 2010 IEEE International Conference on Image Processing.

[3]  Richard G. Baraniuk,et al.  Wavelet-domain compressive signal reconstruction using a Hidden Markov Tree model , 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

[4]  Laurent D. Cohen,et al.  Non-local Regularization of Inverse Problems , 2008, ECCV.

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

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

[7]  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).

[8]  H. Rauhut.  Random Sampling of Sparse Trigonometric Polynomials , 2005, math/0512642.

[9]  Emmanuel J. Candès,et al.  Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information , 2004, IEEE Transactions on Information Theory.

[10]  E. Candès,et al.  Sparsity and incoherence in compressive sampling , 2006, math/0611957.

[11]  Yongdong Zhang,et al.  DR2-Net: Deep Residual Reconstruction Network for Image Compressive Sensing , 2017, Neurocomputing.

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

[13]  Ali Mousavi,et al.  Learning to invert: Signal recovery via Deep Convolutional Networks , 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).