• Corpus ID: 11869289

A Deep Learning Approach to Block-based Compressed Sensing of Images

@article{Adler2016ADL,
  title={A Deep Learning Approach to Block-based Compressed Sensing of Images},
  author={Amir Adler and David Boublil and Michael Elad and Michael Zibulevsky},
  journal={ArXiv},
  year={2016},
  volume={abs/1606.01519}
}
Compressed sensing (CS) is a signal processing framework for efficiently reconstructing a signal from a small number of measurements, obtained by linear projections of the signal. Block-based CS is a lightweight CS approach that is mostly suitable for processing very high-dimensional images and videos: it operates on local patches, employs a low-complexity reconstruction operator and requires significantly less memory to store the sensing matrix. In this paper we present a deep learning… 
View PDF on arXiv
47 Citations
Highly Influential Citations
9
Background Citations
17
Methods Citations
19
Results Citations
2

Figures and Tables from this paper

47 Citations

Deep Learning of Compressed Sensing Operators with Structural Similarity Loss

This paper presents an end-to-end deep learning approach for CS, in which a fully-connected network performs both the linear sensing and non-linear reconstruction stages, using Structural similarity index as loss rather than the standard Mean Squared Error (MSE) loss.

An Efficient Deep Convolutional Laplacian Pyramid Architecture for Cs Reconstruction At Low Sampling Ratios

A deep convolutional Laplacian Pyramid Compressed Sensing Network (LapC-SNet) for CS, which consists of a sampling sub-network and a reconstruction sub- network that is capable of reconstructing more details and sharper edges against the state-of-the-arts methods.

An Efficient Deep Quantized Compressed Sensing Coding Framework of Natural Images

A novel deep network based CS coding framework of natural images that consists of three sub-networks that responsible for sampling, quantization and reconstruction, respectively that can be trained in the form of an end-to-end metric with a proposed rate-distortion optimization loss function.

ADMM-CSNet: A Deep Learning Approach for Image Compressive Sensing

Two versions of a novel deep learning architecture are proposed, dubbed as ADMM-CSNet, by combining the traditional model-based CS method and data-driven deep learning method for image reconstruction from sparsely sampled measurements, which achieved favorable reconstruction accuracy in fast computational speed compared with the traditional and the other deep learning methods.

Sparse representation using compressed sensing via deep learning

The proposed deep learning technique is hired in this article to acquire very CS sparse ternary projections and the overall performance of the proposed STDAENN method is compared with the present strategies primarily based on the imply top signal-to-noise ratio (PSNR) to check the picture nicely.

Deep Neural Network Based Sparse Measurement Matrix for Image Compressed Sensing

A Deep neural network based Sparse Measurement Matrix (DSMM) is learned by the proposed convolutional network to reduce the sampling computational complexity and improve the CS reconstruction performance.

ISTA-Net: Iterative Shrinkage-Thresholding Algorithm Inspired Deep Network for Image Compressive Sensing

This paper proposes a novel structured deep network, dubbed ISTA-Net, which is inspired by the Iterative Shrinkage-Thresholding Algorithm (ISTA) for optimizing a general $l_1$ norm CS reconstruction model, and proposes an accelerated version of ISTA -Net, dubbed FISTA-Net , which isinspired by the fast iterative shrinkage-thresholding algorithm (FISTA).

Compressed Learning for Image Classification: A Deep Neural Network Approach

RQCSNet: A deep learning approach to quantized compressed sensing of remote sensing images

The model has the ability to learn the nonlinear quantization function according to the input data and sending the measured values from the transmitter to the receiver with a fewer bit budget, and it is shown that the quality of image reconstruction will be robust to the noise once adding a noise layer to the network during training.

Classification Guided Deep Convolutional Network for Compressed Sensing

Experimental results demonstrate that the proposed method provides a significant quality improvement in terms of PSNR compared against state-of-the-art methods.

References

SHOWING 1-10 OF 24 REFERENCES

Block Compressed Sensing of Natural Images

  • Lu Gan
  • Computer Science, Mathematics
    2007 15th International Conference on Digital Signal Processing
  • 2007
This paper proposes and study block compressed sensing for natural images, where image acquisition is conducted in a block-by-block manner through the same operator, and shows that the proposed scheme can sufficiently capture the complicated geometric structures of natural images.

Block-Based Compressed Sensing of Images and Video

For multiple-image scenarios, including video and multiview imagery, motion and disparity compensation is employed to exploit frame-to-frame redundancies due to object motion and parallax, resulting in residual frames which are more compressible and thus more easily reconstructed from compressed-sensing measurements.

Block compressed sensing of images using directional transforms

Block-based random image sampling is coupled with a projection-driven compressed-sensing recovery that encourages sparsity in the domain of directional transforms simultaneously with a smooth reconstructed image, yielding images with quality that matches or exceeds that produced by a popular, yet computationally expensive, technique which minimizes total variation.

Compressed-sensing recovery of images and video using multihypothesis predictions

Experimental results demonstrate that the proposed reconstructions outperform alternative strategies not employing multihypothesis predictions, and a Tikhonov regularization to an ill-posed least-squares optimization is proposed.

Multiscale block compressed sensing with smoothed projected Landweber reconstruction

Experimental results reveal that the proposed multiscale reconstruction preserves the fast computation associated with block-based compressed sensing while rivaling the reconstruction quality of a popular total-variation algorithm known for both its high-quality reconstruction as well as its exceedingly large computational cost.

Sparsity and Compressed Sensing in Radar Imaging

The accessible framework provided by compressed sensing illuminates the impact of joining these themes and potential future directions are conjectured both for extension of theory motivated by practice and for modification of practice based on theoretical insights.

Fast $\ell_1$ -SPIRiT Compressed Sensing Parallel Imaging MRI: Scalable Parallel Implementation and Clinically Feasible Runtime

We present l1 -SPIRiT, a simple algorithm for auto calibrating parallel imaging (acPI) and compressed sensing (CS) that permits an efficient implementation with clinically-feasible runtimes. We…

Image denoising: Can plain neural networks compete with BM3D?

This work attempts to learn this mapping directly with a plain multi layer perceptron (MLP) applied to image patches and shows that by training on large image databases it is able to compete with the current state-of-the-art image denoising methods.

Compressed Sensing MRI

The authors emphasize on an intuitive understanding of CS by describing the CS reconstruction as a process of interference cancellation, and there is also an emphasis on the understanding of the driving factors in applications.

Received-Signal-Strength-Based Indoor Positioning Using Compressive Sensing

Experimental results indicate that the proposed RSS-based indoor positioning system leads to substantial improvement on localization accuracy and complexity over the widely used traditional fingerprinting methods.