The popularity of the CLEAN algorithm in radio interferometric imaging stems from its maturity, speed, and robustness. While many alternatives have been proposed in the literature, none have achieved mainstream adoption by astronomers working with data from interferometric arrays operating in the big data regime. This lack of adoption is largely due to increased computational complexity, absence of mature implementations, and the need for astronomers to tune obscure algorithmic parameters. This work introduces pfb-imaging: a flexible library that implements the scaffolding required to develop and accelerate general radio interferometric imaging algorithms. We demonstrate how the framework can be used to implement a sparsity-based image reconstruction technique known as (unconstrained) SARA in a way that scales with image size rather than data volume and features interpretable algorithmic parameters. The implementation is validated on terabyte-sized data from the MeerKAT telescope, using both a single compute node and Amazon Web Services computing instances.

We contribute to an uncertainty quantification problem in imaging that evaluates a hypothesis test questioning the existence of local “artifacts” appearing in the maximum a posteriori (MAP) estimate (obtained from standard numerical tools). Such a method, called Bayesian uncertainty quantification by optimization (BUQO), was introduced a few years ago as an efficient and scalable alternative to sampling methods when per-pixel error bars are not needed. BUQO formulates a hypothesis test for probing the existence of local structures in the MAP estimate as a minimization problem that can be solved efficiently with standard optimization algorithms. In this context, BUQO requires a “mathematical” definition of the “local artifact.” This definition can be interpreted as an inpainting of the structure. However, only simple handcrafted techniques have been proposed so far due to the complexity of the problem. In this work, we propose a data-driven alternative to BUQO where the inpainting procedure in the algorithm is performed using a convolutional inpainting neural network (NN). This results in a plug-and-play algorithm, based on the primal-dual Condat–Vũ iterations, where the inpainting procedure is performed with a NN. The proposed approach is assessed on two image reconstruction problems inspired by medicine. We specifically perform simulations on two Fourier undersampling problems (discrete and non-uniform) encountered in magnetic resonance imaging, as well as a computed tomography problem using the Radon measurement operator.

In this work we study the behavior of the forward-backward (FB) algorithm when the proximity operator is replaced by a sub-iterative procedure to approximate a Gaussian denoiser, in a Plug-and-Play (PnP) fashion. In particular, we consider both analysis and synthesis Gaussian denoisers within a dictionary framework, obtained by unrolling dual-FB iterations or FB iterations, respectively. We analyze the associated minimization problems as well as the asymptotic behavior of the resulting FB-PnP iterations. In particular, we show that the synthesis Gaussian denoising problem can be viewed as a proximity operator. For each case, analysis and synthesis, we show that the FB-PnP algorithms solve the same problem whether we use only one or an infinite number of sub-iteration to solve the denoising problem at each iteration. To this aim, we show that each "one sub-iteration" strategy within the FB-PnP can be interpreted as a primal-dual algorithm when a warm-restart strategy is used. We further present similar results when using a Moreau-Yosida smoothing of the global problem, for an arbitrary number of sub-iterations. Finally, we provide numerical simulations to illustrate our theoretical results. In particular we first consider a toy compressive sensing example, as well as an image restoration problem in a deep dictionary framework.

Markov Chain Monte Carlo (MCMC) algorithms are standard approaches to solve imaging inverse problems and quantify estimation uncertainties, a key requirement in absence of ground-truth data. To improve estimation quality, Plug-and-Play MCMC algorithms, such as PnP-ULA, have been recently developed to accommodate priors encoded by a denoising neural network. Designing scalable samplers for high-dimensional imaging inverse problems remains a challenge: drawing and storing high-dimensional samples can be prohibitive, especially for high-resolution images. To address this issue, this work proposes a distributed sampler based on approximate data augmentation and PnP-ULA to solve very large problems. The proposed sampler uses lightweight denoising convolutional neural network, to efficiently exploit multiple GPUs on a Single Program Multiple Data architecture. Reconstruction performance and scalability are evaluated on several imaging problems. Communication and computation overheads due to the denoiser are carefully discussed. The proposed distributed approach noticeably combines three very precious qualities: it is scalable, enables uncertainty quantification, for a reconstruction performance comparable to other PnP methods.

State-space models (SSM) are common in signal processing, where Kalman smoothing (KS) methods are state-of-the-art. However, traditional KS techniques lack expressivity as they do not incorporate spatial prior information. Recently, [1] proposed an ADMM algorithm that handles the state-space fidelity term with KS while regularizing the object via a sparsity-based prior with proximity operators. Plug-and-Play (PnP) methods are a popular type of iterative algorithms that replace proximal operators encoding prior knowledge with powerful denoisers such as deep neural networks. These methods are widely used in image processing, achieving state-of-the-art results. In this work, we build on the KS-ADMM method, combining it with deep learning to achieve higher expressivity. We propose a PnP algorithm based on KS-ADMM iterations, efficiently handling the SSM through KS, while enabling the use of powerful denoising networks. Simulations on a 2D+t imaging problem show that the proposed PnP-KS-ADMM algorithm improves the computational efficiency over standard PnP-ADMM for large numbers of timesteps.

Markov Chain Monte Carlo (MCMC) methods enable uncertainty quantification in inverse problems, making them valuable in various applications, especially when no ground-truth is available. Optimization-inspired Plug-and-Play MCMC algorithms, like PnP-ULA, have been developed to incorporate rich neural networks as priors, improving drastically the estimation quality. However, scaling MCMC samplers remains challenging, as generating and storing a sufficient number of high-dimensional samples, typically high-resolution images, can be computationally prohibitive. This work proposes a distributed implementation of PnP-ULA to target much larger problems without compromising on estimation quality. The proposed approach leverages a lightweight deep denoiser within a Single Program Multiple Data that permits an efficient exploitation of a multi-GPU architecture. Synthetic imaging tasks demonstrate the scalability and performance of this strategy to deal with very high dimensional inverse problems. This approach achieves competitive estimation quality along with uncertainty quantification compared to a typical state-of-the-art PnP optimization method, with much higher scalability.

In this paper, we present a new edge detection model based on proximal unfolded neural networks. The architecture relies on unfolding proximal Blake-Zisserman iterations, leading to a composition of two blocks: a smoothing block and an edge detection block. We show through simulations that the proposed approach efficiently eliminates irrelevant details while retaining key edges and significantly improves performance with respect to state-of-the-art strategies. Additionally, our architecture is significantly lighter than recent learning models designed for edge detection in terms of number of learnable parameters and inference time.

. Asymptotic analysis of generic stochastic algorithms often relies on descent conditions. In a convex setting, some technical shortcuts can be considered to establish asymptotic convergence guarantees of the associated scheme. However, in a non-convex setting, obtaining similar guarantees is usually more complicated, and relies on the use of the Kurdyka- Lojasiewicz (K L) property. While this tool has become popular in the field of deterministic optimization, it is much less widespread in the stochastic context and the few works making use of it are essentially based on trajectory-by-trajectory approaches. In this paper, we propose a new framework for using the K L property in a non-convex stochastic setting based on conditioning theory. We show that this framework allows for deeper asymptotic investigations on stochastic schemes verifying some generic descent conditions. We further show that our methodology can be used to prove convergence of generic stochastic gradient descent (SGD) schemes, and unifies conditions investigated in multiple articles of the literature.

This work focuses on joint image denoising and contour detection. On the one hand, contour detection on clean images (without noise) has been extensively studied from both variational formulation and deep learning perspectives. On the other hand, although the task of jointly denoising and contour detection has been largely considered in image processing literature using variational formulations, it has not been handled from the model-based neural network perspective. In this work, we propose an unfolded discrete Mumford-Shah procedure that enables us to bridge the gap between standard variational procedures designed to perform the combined denoising/edge detection task and black-box neural network designed for edge detection purpose.

This article introduces a novel approach to learning monotone neural networks through a newly defined penalization loss. The proposed method is particularly effective in solving classes of variational problems, specifically monotone inclusion problems, commonly encountered in image processing tasks. The Forward-Backward-Forward (FBF) algorithm is employed to address these problems, offering a solution even when the Lipschitz constant of the neural network is unknown. Notably, the FBF algorithm provides convergence guarantees under the condition that the learned operator is monotone. Building on plug-and-play methodologies, our objective is to apply these newly learned operators to solving non-linear inverse problems. To achieve this, we initially formulate the problem as a variational inclusion problem. Subsequently, we train a monotone neural network to approximate an operator that may not inherently be monotone. Leveraging the FBF algorithm, we then show simulation examples where the non-linear inverse problem is successfully solved.

Sampling-based algorithms are classical approaches to perform Bayesian inference in inverse problems. They provide estimators with the associated credibility intervals to quantify the uncertainty on the estimators. Although these methods hardly scale to high dimensional problems, they have recently been paired with optimization techniques, such as proximal and splitting approaches, to address this issue. Such approaches pave the way to distributed samplers, splitting computations to make inference more scalable and faster. We introduce a distributed Split Gibbs sampler (SGS) to efficiently solve such problems involving distributions with multiple smooth and non-smooth functions composed with linear operators. The proposed approach leverages a recent approximate augmentation technique reminiscent of primal-dual optimization methods. It is further combined with a block-coordinate approach to split the primal and dual variables into blocks, leading to a distributed block-coordinate SGS. The resulting algorithm exploits the hypergraph structure of the involved linear operators to efficiently distribute the variables over multiple workers under controlled communication costs. It accommodates several distributed architectures, such as the Single Program Multiple Data and client-server architectures. Experiments on a large image deblurring problem show the performance of the proposed approach to produce high quality estimates with credibility intervals in a small amount of time. Supplementary material to reproduce the experiments is available online.

A common approach to solve inverse imaging problems relies on finding a maximum a posteriori (MAP) estimate of the original unknown image, by solving a minimization problem. In this context, iterative proximal algorithms are widely used, enabling to handle non-smooth functions and linear operators. Recently, these algorithms have been paired with deep learning strategies, to further improve the estimate quality. In particular, proximal neural networks (PNNs) have been introduced, obtained by unrolling a proximal algorithm as for finding a MAP estimate, but over a fixed number of iterations, with learned linear operators and parameters. As PNNs are based on optimization theory, they are very flexible, and can be adapted to any image restoration task, as soon as a proximal algorithm can solve it. They further have much lighter architectures than traditional networks. In this article we propose a unified framework to build PNNs for the Gaussian denoising task, based on both the dual-FB and the primal-dual Chambolle-Pock algorithms. We further show that accelerated inertial versions of these algorithms enable skip connections in the associated NN layers. We propose different learning strategies for our PNN framework, and investigate their robustness (Lipschitz property) and denoising efficiency. Finally, we assess the robustness of our PNNs when plugged in a forward-backward algorithm for an image deblurring problem.

Unfolded proximal neural networks (PNNs) form a family of methods that combines deep learning and proximal optimization approaches. They consist in designing a neural network for a specific task by unrolling a proximal algorithm for a fixed number of iterations, where linearities can be learned from prior training procedure. PNNs have shown to be more robust than traditional deep learning approaches while reaching at least as good performances, in particular in computational imaging. However, training PNNs still depends on the efficiency of available training algorithms. In this work, we propose a lifted training formulation based on Bregman distances for unfolded PNNs. Leveraging the deterministic mini-batch block-coordinate forward-backward method, we design a bespoke computational strategy beyond traditional back-propagation methods for solving the resulting learning problem efficiently. We assess the behaviour of the proposed training approach for PNNs through numerical simulations on image denoising, considering a denoising PNN whose structure is based on dual proximal-gradient iterations.

This paper presents a multilevel algorithm specifically designed for radio-interferometric imaging in astronomy. The proposed algorithm is used to solve the uSARA (unconstrained Sparsity Averaging Reweighting Analysis) formulation of this image restoration problem. Multilevel algorithms rely on a hierarchy of approximations of the objective function to accelerate its optimization. In contrast to the usual multilevel approaches where this hierarchy is derived in the parameter space, here we construct the hierarchy of approximations in the observation space. The proposed approach is compared to a reweighted forward-backward procedure, which is the backbone iteration scheme for solving the uSARA problem.

Optical fibers aim to image in vivo biological processes. In this context, high spatial resolution and stability to fiber movements are key to enable decision-making processes (e.g. for microendoscopy). Recently, a single-pixel imaging technique based on a multicore fiber photonic lantern has been designed, named computational optical imaging using a lantern (COIL). A proximal algorithm based on a sparsity prior, dubbed SARA-COIL, has been further proposed to solve the associated inverse problem, to enable image reconstructions for high resolution COIL microendoscopy. In this work, we develop a data-driven approach for COIL. We replace the sparsity prior in the proximal algorithm by a learned denoiser, leading to a plug-and-play (PnP) algorithm. The resulting PnP method, based on a proximal primal-dual algorithm, enables to solve the Morozov formulation of the inverse problem. We use recent results in learning theory to train a network with desirable Lipschitz properties, and we show that the resulting primal-dual PnP algorithm converges to a solution to a monotone inclusion problem. Our simulations highlight that the proposed data-driven approach improves the reconstruction quality over variational SARA-COIL method on both simulated and real data.

Computed tomography (CT) imaging of the thorax is widely used for the detection and monitoring of pulmonary embolism (PE). However, CT images can contain artifacts due to the acquisition or the processes involved in image reconstruction. Radiologists often have to distinguish between such artifacts and actual PEs. We provide a proof of concept in the form of a scalable hypothesis testing method for CT, to enable quantifying uncertainty of possible PEs. In particular, we introduce a Bayesian Framework to quantify the uncertainty of an observed compact structure that can be identified as a PE. We assess the ability of the method to operate under high-noise environments and with insufficient data.

Uncertainty quantification in image restoration is a prominent challenge, mainly due to the high dimensionality of the encountered problems. Recently, a Bayesian uncertainty quantification by optimization (BUQO) has been proposed to formulate hypothesis testing as a minimization problem. The objective is to determine whether a structure appearing in a maximum a posteriori estimate is true or is a reconstruction artifact due to the ill-posedness or ill-conditioness of the problem. In this context, the mathematical definition of having a ``fake structure" is crucial, and highly depends on the type of structure of interest. This definition can be interpreted as an inpainting of a neighborhood of the structure, but only simple techniques have been proposed in the literature so far, due to the complexity of the problem. In this work, we propose a data-driven method using a simple convolutional neural network to perform the inpainting task, leading to a novel plug-and-play BUQO algorithm. Compared to previous works, the proposed approach has the advantage that it can be used for a wide class of structures, without needing to adapt the inpainting operator to the area of interest. In addition, we show through simulations on magnetic resonance imaging, that compared to the original BUQO's hand-crafted inpainting procedure, the proposed approach provides greater qualitative output images. Python code will be made available for reproducibility upon acceptance of the article.

Neural networks have become ubiquitous tools for solving signal and image processing problems, and they often outperform standard approaches. Nevertheless, training neural networks is a challenging task in many applications. The prevalent training procedure consists of minimizing highly non-convex objectives based on data sets of huge dimension. In this context, current methodologies are not guaranteed to produce global solutions. We present an alternative approach which foregoes the optimization framework and adopts a variational inequality formalism. The associated algorithm guarantees convergence of the iterates to a true solution of the variational inequality and it possesses an efficient block-iterative structure. A numerical application is presented.

Stochastic differentiable approximation schemes are widely used for solving high dimensional problems. Most of existing methods satisfy some desirable properties, including conditional descent inequalities, and almost sure (a.s.) convergence guarantees on the objective function, or on the involved gradient. However, for non-convex objective functions, a.s. convergence of the iterates, i.e., the stochastic process, to a critical point is usually not guaranteed, and remains an important challenge. In this article, we develop a framework to bridge the gap between descent-type inequalities and a.s. convergence of the associated stochastic process. Leveraging a novel Kurdyka-Lojasiewicz property, we show convergence guarantees of stochastic processes under mild assumptions on the objective function. We also provide examples of stochastic algorithms benefiting from the proposed framework and derive a.s. convergence guarantees on the iterates.