Image Reconstruction Based on Deep Iterative Shrinkage Network

With the aim of developing a fast yet accurate algorithm for compressive sensing (CS) reconstruction of natural images, we combine in this paper the merits of two existing categories of CS methods: the structure insights of traditional optimization-based methods and the speed of recent network-based ones. Specifically, we propose a novel structured deep network, dubbed ISTA-Net, which is inspired by the Iterative Shrinkage-Thresholding Algorithm (ISTA) for optimizing a general $$ norm CS reconstruction model. To cast ISTA into deep network form, we develop an effective strategy to solve the proximal mapping associated with the sparsity-inducing regularizer using nonlinear transforms. All the parameters in ISTA-Net (e.g. nonlinear transforms, shrinkage thresholds, step sizes, etc.) are learned end-to-end, rather than being hand-crafted. Moreover, considering that the residuals of natural images are more compressible, an enhanced version of ISTA-Net in the residual domain, dubbed ISTA-Net+, is derived to further improve CS reconstruction. Extensive CS experiments demonstrate that the proposed ISTA-Nets outperform existing state-of-the-art optimization-based and network-based CS methods by large margins, while maintaining fast computational speed. Our source codes are available: http://jianzhang.tech/projects/ISTA-Net.

Compressive sensing (CS) is a technique that enables the recovery of sparse signals using fewer measurements than traditional sampling methods. To address the computational challenges of CS reconstruction, our objective is to develop an interpretable and concise neural network model for reconstructing natural images using CS. We achieve this by mapping one step of the iterative shrinkage thresholding algorithm (ISTA) to a deep network block, representing one iteration of ISTA. To enhance learning ability and incorporate structural diversity, we integrate aggregated residual transformations (ResNeXt) and squeeze‐and‐excitation mechanisms into the ISTA block. This block serves as a deep equilibrium layer connected to a semi‐tensor product network for convenient sampling and providing an initial reconstruction. The resulting model, called MsDC‐DEQ‐Net, exhibits competitive performance compared to state‐of‐the‐art network‐based methods. It significantly reduces storage requirements compared to deep unrolling methods, using only one iteration block instead of multiple iterations. Unlike deep unrolling models, MsDC‐DEQ‐Net can be iteratively used, gradually improving reconstruction accuracy while considering computation tradeoffs. Additionally, the model benefits from multiscale dilated convolutions, further enhancing performance.

This paper focuses on processing low oversampling echo data of staggered synthetic aperture radar (SAR). In staggered mode, the non-uniformly sampling and echo data loss cause severe azimuth ambiguity. To solve this problem, we propose a method combining the compressed sensing (CS) tool and the conformal Fourier transform (CFT) algorithm. First, the 2-D-fast iterative shrinkage thresholding algorithm (FISTA) is used to efficiently solve the optimization problem based on CS theory to recovery the missing data. Second, the CFT algorithm is used to accurately compute the spectrum of the non-uniformly sampled echo data. Unlike other methods suiting fast pulse repetition interval (PRI) change only, this method performs well for both fast and slow PRI change. Plus, the proposed method can be well applied to both point and distributed targets. Simulation results demonstrate that the proposed method can effectively and robustly suppress the azimuth ambiguity for staggered SAR data.

The most common technique for generating B-mode ultrasound (US) images is delay-and-sum (DAS) beamforming, where the signals received at the transducer array are sampled before an appropriate delay is applied. This necessitates sampling rates exceeding the Nyquist rate and the use of a large number of antenna elements to ensure sufficient image quality. Recently, we proposed methods to reduce the sampling rate and the array size relying on image recovery using iterative algorithms based on compressed sensing (CS) and the finite rate of innovation (FRI) frameworks. Iterative algorithms typically require a large number of iterations, making them difficult to use in real time. In this article, we propose a reconstruction method from sub-Nyquist samples in the time and spatial domain, which is based on unfolding the iterative shrinkage thresholding algorithm (ISTA), resulting in an efficient and interpretable deep network. The inputs to our network are the subsampled beamformed signals after summation and delay in the frequency domain, requiring only a subset of the US signal to be stored for recovery. Our method allows reducing the number of array elements, sampling rate, and computational time while ensuring high-quality imaging performance. Using in vivo data, we demonstrate that the proposed method yields high-quality images while reducing the data volume traditionally used up to 36 times. In terms of image resolution and contrast, our technique outperforms previously suggested methods as well as DAS and minimum-variance (MV) beamforming, paving the way to real-time applicable recovery methods.

Compressed sensing (CS) reconstruction of nonsparse scenes is one of the difficulties in synthetic aperture radar (SAR) imaging technology. Although the conventional CS method with sparse representation has proven applicable for nonsparse SAR reconstruction, its disadvantages are unsatisfactory imaging quality and high computational complexity under downsampling. In this paper, a novel deep learning approach for nonsparse SAR scene reconstruction is proposed based on sparse representation and the iterative shrinkage threshold algorithm (ISTA). Specifically, we first develop a sparse representation-based imaging model associated with the ℓ₁ sparse regularizer in nonlinear transform domains. Then, the advantages of the recurrent neural network (RNN) and convolutional neural network (CNN) are incorporated into an ISTA-inspired deep unfolded network (DUN) called SR-ISTA-Net, in which all the parameters are layer-varied rather than handcrafted. The experiments verify that the proposed SR-ISTA-Net can provide high-quality reconstruction results under nonsparse scenes while substantially reducing imaging time.

Sparse-representation-based synthetic aperture radar (SAR) imaging technology has shown superior potential in the reconstruction of nonsparse scenes. However, many existing compressed sensing (CS) methods with sparse representation cannot obtain an optimal sparse basis and only apply to the sensing matrix obtained by exact observation, resulting in a low image quality occupying more storage space. To reduce the computational cost and improve the imaging performance of nonsparse scenes, we formulate a deep learning SAR imaging method based on sparse representation and approximated observation deduced from the chirp-scaling algorithm (CSA). First, we incorporate the CSA-derived approximated observation model and a nonlinear transform function within a sparse reconstruction framework. Second, an iterative shrinkage threshold algorithm is adopted to solve this framework, and the solving process is unfolded as a deep SAR imaging network. Third, a dual-path convolutional neural network (CNN) block is designed in the network to achieve the nonlinear transform, dramatically improving the sparse representation capability over conventional transform-domain-based CS methods. Last, we improve the CNN block to develop an enhanced version of the deep SAR imaging network, in which all the parameters are layer-varied and trained by supervised learning. The experiments demonstrate that our proposed two imaging networks outperform conventional CS-driven and deep-learning-based methods in terms of computing efficiency and reconstruction performance of nonsparse scenes.

In the past decade, the compressive sensing (CS) based ISAR imaging methods have gained much interest due to the capability of obtaining high-quality images with under-sampled data. However, both the performance and the application of CS ISAR imaging methods are limited by sparse representations and iterative reconstruction algorithms where the former may be hard to find and the latter may lead to low imaging efficiency. The deep-network (DN) based image reconstruction methods appeared in recent years have been shown to be able to dramatically reduce the computational complexity and ensure the image reconstruction at the same time. The Deep-ADMM-Net (DAN) is a network constructed by iterative steps of the traditional optimization algorithm, Alternating Direction Method of Multipliers (ADMM). The mainly characteristic of DAN is that it is interpretable and efficient. We propose a DAN based ISAR imaging method. The well trained DAN can reconstruct high-quality ISAR image using much fewer measurements than CS based imaging methods. Experimental results show that our proposed imaging method is superior to the existing CS method in both image reconstruction quality and computational efficiency

Due to proper use of the image sparsity, CS (compressed sensing) image compression has made great achievements in the field of image compression without the constraint of Nyquist sampling law. A great deal of researches indicate that there exist obvious statistical and structural priors regularity for image information distribution, while traditional CS image compression algorithms only use the sparse characteristic of the image information. In this paper, we propose a CS image reconstruction algorithm based on the joint statistical and structural priors which can achieve efficient image reconstruction via a small amount of measurements. With the full use of inter-scale and intra-scale relations of the sparse coefficients, we optimize the iterative hard thresholding CS algorithm specifically by building a GSM model to constrain the local coefficients distribution statistically, and a tree model to constrain the global coefficients distribution structurally. Extensive simulations have been conducted and the results show that the proposed method has achieved a considerable promotion both on the speed and the PSNR gain of image reconstruction, compared with the traditional recovery algorithms under the same compression ratio.

Classical single additive noise forward model can be extended to account for different uncertainties by variable splitting models. For example, one can distinguish between observation noise and forward model uncertainty or even to account for other forward model uncertainties. In this paper, we consider different cases and propose to use the Bayesian approach to handle them. As a by-product, we see that when MAP estimator is used we can find the same kind of optimization algorithms as Alternating Direction Method of Multipliers (ADMM) or Iterative Shrinkage Thresholding Algorithm (ISTA) optimization ones. However, the Bayesian approach gives us the tools to go further by estimating the hyperparameters of the inversion problems which are often crucial in real applications.

Compressed sensing (CS) is a technique to sample compressible signals below the Nyquist rate, whilst still allowing near optimal reconstruction of the signal. In this paper, we apply the iterative hard thresholding (IHT) algorithm for compressed sensing on the speech signal. The interested speech signal is transformed to the frequency domain using Discrete Fourier Transform (DCT) and then compressed sensing is applied to that signal. The compressed signal can be reconstructed using the recently introduced Iterative Hard Thresholding (IHT) algorithm and also by the tradditional \( \ell_{1} \) minimization (basic pursuit) for comparison. It is shown that the compressed sensing can provide better root mean square error (RMSE) than the tradition DCT compression method, given the same compression ratio.

We present two model-based neural network architectures purposed for sporadic user detection and channel estimation in massive machine-type communications. In the scenario under consideration, a base station assigns the users a set of pilot sequences that is linearly dependent, but because user activity is sporadic the detection/estimation problem is amenable to sparse recovery algorithms. Further, we consider a millimeter-wave wireless channel, so that the channel vectors are sparse in a known dictionary. We apply the deep unfolding framework to design custom neural network layers by unrolling two iterative optimization algorithms: (1) linearized alternating direction method of multipliers, which we apply to a constrained convex problem, and (2) vector approximate message passing featuring a novel denoiser based on the iterative shrinkage thresholding algorithm. The networks thus inherit domain knowledge as encapsulated by the signal model, and suitable operations as informed by the algorithms—in the same spirit as convolutional networks that exploit structure inherent in images and audio, except grounded in optimization and statistics. The networks, trained on synthetic data generated from the block-fading millimeter-wave multiple access channel model, offer improved complexity and accuracy relative to their iterative counterparts, and are potentially a boon to cell-free MIMO systems.

In recent years, extensive research has shown that deep learning-based compressed image reconstruction algorithms can achieve faster and better high-quality reconstruction for single-pixel imaging, and that reconstruction quality can be further improved by joint optimization of sampling and reconstruction. However, these network-based models mostly adopt end-to-end learning, and their structures are not interpretable. In this paper, we propose SRMU-Net, a sampling and reconstruction jointly optimized model unfolding network. A fully connected layer or a large convolutional layer that simulates compressed reconstruction is added to the compressed reconstruction network, which is composed of multiple cascaded iterative shrinkage thresholding algorithm (ISTA) unfolding iteration blocks. To achieve joint optimization of sampling and reconstruction, a specially designed network structure is proposed so that the sampling matrix can be input into ISTA unfolding iteration blocks as a learnable parameter. We have shown that the proposed network outperforms the existing algorithms by extensive simulations and experiments.

Synthetic aperture radar tomography (TomoSAR) has been extensively employed in 3-D reconstruction in dense urban areas using high-resolution SAR acquisitions. Compressive sensing (CS)-based algorithms are generally considered as the state-of-the art in super-resolving TomoSAR, in particular in the single look case. This superior performance comes at the cost of extra computational burdens, because of the sparse reconstruction, which cannot be solved analytically, and we need to employ computationally expensive iterative solvers. In this article, we propose a novel deep learning-based super-resolving TomoSAR inversion approach, γ-Net, to tackle this challenge. γ-Net adopts advanced complex-valued learned iterative shrinkage thresholding algorithm (CV-LISTA) to mimic the iterative optimization step in sparse reconstruction. Simulations show the height estimate from a well-trained γ-Net approaches the Cramér-Rao lower bound (CRLB) while improving the computational efficiency by one to two orders of magnitude comparing to the first-order CS-based methods. It also shows no degradation in the super-resolution power comparing to the state-of-the-art second-order TomoSAR solvers, which are much more computationally expensive than the first-order methods. Specifically, γ-Net reaches more than 90% detection rate in moderate super-resolving cases at 25 measurements at 6 dB SNR. Moreover, simulation at limited baselines demonstrates that the proposed algorithm outperforms the second-order CS-based method by a fair margin. Test on real TanDEM-X data with just six interferograms also shows high-quality 3-D reconstruction with high-density detected double scatterers.

Synthetic aperture radar tomography (TomoSAR) has been widely employed in 3-D urban mapping. However, state-of-the-art super-resolving TomoSAR algorithms are computationally expensive, because conventional numerical solvers need to solve the <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$l_{2^{-}}l_{1}$</tex> mix norm minimization. This paper proposes a computationally efficient super-resolving To-moSAR inversion algorithm based on deep learning. We studied the potential of deep learning to mimic a conventional <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$l_{2}-l_{1}$</tex> mix norm solver, i.e. iterative shrinkage thresholding algorithm (ISTA), and proposed several improvements of the complex-valued learned ISTA for TomoSAR inversion. Investigation on the super-resolution ability and estimator efficiency of the proposed algorithm shows that the proposed algorithm approaches the Cramer Rao lower bound (CRLB) with a computational efficiency more than 100 times better than the conventional solver.

In this paper, an image deconvolution problem using triangular wavelets is addressed. A simple blurred image is generated by the Gaussian-based blur kernel and additive Gaussian white noise. Two-dimensional orthogonal Haar wavelets on a triangular lattice, which gives sparse and isotropie representations of images, are selected as a dictionary. Using the iterative shrinkage threshold algorithm, some numerical experiments are carried out for the problem of recovering the original image from the noisy blurred image. We show that the triangular wavelets result in better performance than the conventional Haar wavelet transform.