Selecting an appropriate prior to compensate for information loss due to the measurement operator is a fundamental challenge in imaging inverse problems. Implicit priors based on denoising neural networks have become central to widely-used frameworks such as Plug-and-Play (PnP) algorithms. In this work, we introduce Fixed-points of Restoration (FiRe) priors as a new framework for expanding the notion of priors in PnP to general restoration models beyond traditional denoising models. The key insight behind FiRe is that smooth images emerge as fixed points of the composition of a degradation operator with the corresponding restoration model. This enables us to derive an explicit formula for our implicit prior by quantifying invariance of images under this composite operation. Adopting this fixed-point perspective, we show how various restoration networks can effectively serve as priors for solving inverse problems. The FiRe framework further enables ensemble-like combinations of multiple restoration models as well as acquisition-informed restoration networks, all within a unified optimization approach. Experimental results validate the effectiveness of FiRe across various inverse problems, establishing a new paradigm for incorporating pretrained restoration models into PnP-like algorithms. Code available at https://github.com/matthieutrs/fire.

Plug-and-play algorithms constitute a popular frame- work for solving inverse imaging problems that rely on the implicit definition of an image prior via a denoiser. These algorithms can leverage powerful pretrained denoisers to solve a wide range of imaging tasks, circumventing the necessity to train models on a per-task basis. Unfortunately, plug-and-play methods often show unstable behaviors, hampering their promise of versatility and leading to suboptimal quality of reconstructed images. In this work, we show that enforcing equivariance to certain groups of transformations (rotations, reflections, and/or translations) on the denoiser strongly improves the stability of the algorithm as well as its reconstruction quality. We provide a theoretical analysis that illustrates the role of equivariance on better performance and stability. We present a simple algorithm that enforces equivariance on any existing denoiser by simply applying a random transformation to the input of the denoiser and the inverse transformation to the output at each iteration of the algorithm. Experiments on multiple imaging modalities and denoising networks show that the equivariant plug-and-play algorithm improves both the reconstruction performance and the stability compared to their non-equivariant counterparts.

We propose a new approach for large-scale high-dynamic range computational imaging. Deep Neural Networks (DNNs) trained end-to-end can solve linear inverse imaging problems almost instantaneously. While unfolded architectures provide robustness to measurement setting variations, embedding large-scale measurement operators in DNN architectures is impractical. Alternative Plug-and-Play (PnP) approaches, where the denoising DNNs are blind to the measurement setting, have proven effective to address scalability and high-dynamic range challenges, but rely on highly iterative algorithms. We propose a residual DNN series approach, also interpretable as a learned version of matching pursuit, where the reconstructed image is a sum of residual images progressively increasing the dynamic range, and estimated iteratively by DNNs taking the back-projected data residual of the previous iteration as input. We demonstrate on radio-astronomical imaging simulations that a series of only few terms provides a reconstruction quality competitive with PnP, at a fraction of the cost.

This paper presents an investigation into the zero-shot performance of pre-trained foundation models on remote sensing tasks. Recent advances in self-supervised learning suggest that these models, when trained on vast amounts of unsupervised data, could potentially improve generalization across a number of downstream tasks. Our study offers an empirical evaluation of these models on standard remote-sensing benchmarks such as EuroSAT and BigEarthNet-S2, with the intent to confirm whether these models have encountered satellite imagery during their training phase. Moreover, we examine the impact of adding a geospatial domain-specific textual description of classes, contrasting it with the standard class-based prompts. Our findings indicate that the fine-tuned BLIP models exhibit superior zero-shot performance on these benchmarks compared to their standard counterparts, signifying that fine-tuning on standard benchmarks enhances performance. Furthermore, the addition of geospatial context variably influences performance depending on the specific model and dataset. This work provides crucial insights into the applicability of foundation models in remote sensing tasks and lays the groundwork for further research.

Large datasets of geospatial satellite images are available online, exhibiting significant variations in both image quality and content. These variations in image quality stem from the image processing pipeline and image acquisition settings, resulting in subtle differences within datasets of images acquired with the same satellites. Recent progress in the field of image processing have considerably enhanced capabilities in noise and artifacts removal, as well as image super-resolution. Consequently, this opens up possibilities for homogenizing geospatial image datasets by reducing the intra-dataset variations in image quality. In this work, we show that conventional image detection and segmentation neural networks trained on geospatial data are robust neither to noise and artefact removal preprocessing, nor to mild resolution variations.

Image restoration has long been one of the key research topics in image processing. Many mathematical approaches have been developed to solve this problem, e.g., variational methods, wavelet techniques, or Bayesian methods. With the widespread of neural network (NN) models in all the subdomains of data science, the performance limits of these methods are further pushed. One of the most successful strategies consists of plugging NNs in existing optimization algorithms. However, so doing raises several mathematical and practical challenges. One of the main issues is to secure the convergence of the resulting iterative scheme. Further questions concerning the characterization of the reached limit are also worth being addressed. In this paper, we show that the theory of maximally monotone operators allows us to bring insightful answers to these problems and to design firmly nonexpansive NNs; combining these with postprocessing NNs leads to excellent global restoration quality.

We introduce a new paradigm for solving regularized variational problems. These are typically formulated to address ill-posed inverse problems encountered in signal and image processing. The objective function is traditionally defined by adding a regularization function to a data fit term, which is subsequently minimized by using iterative optimization algorithms. Recently, several works have proposed to replace the operator related to the regularization by a more sophisticated denoiser. These approaches, known as plug-and-play (PnP) methods, have shown excellent performance. Although it has been noticed that, under some Lipschitz properties on the denoisers, the convergence of the resulting algorithm is guaranteed, little is known about characterizing the asymptotically delivered solution. In the current article, we propose to address this limitation. More specifically, instead of employing a functional regularization, we perform an operator regularization, where a maximally monotone operator (MMO) is learned in a supervised manner. This formulation is flexible as it allows the solution to be characterized through a broad range of variational inequalities, and it includes convex regularizations as special cases. From an algorithmic standpoint, the proposed approach consists in replacing the resolvent of the MMO by a neural network (NN). We present a universal approximation theorem proving that nonexpansive NNs are suitable models for the resolvent of a wide class of MMOs. The proposed approach thus provides a sound theoretical framework for analyzing the asymptotic behavior of first-order PnP algorithms. In addition, we propose a numerical strategy to train NNs corresponding to resolvents of MMOs. We apply our approach to image restoration problems and demonstrate its validity in terms of both convergence and quality.

Building nonexpansive Convolutional Neural Networks (CNNs) is a challenging problem that has recently gained a lot of attention from the image processing community. In particular, it appears to be the key to obtain convergent Plugand-Play algorithms. This problem, which relies on an accurate control of the the Lipschitz constant of the convolutional layers, has also been investigated for Generative Adversarial Networks to improve robustness to adversarial perturbations. However, to the best of our knowledge, no efficient method has been developed yet to build nonexpansive CNNs. In this paper, we develop an optimization algorithm that can be incorporated in the training of a network to ensure the nonexpansiveness of its convolutional layers. This is shown to allow us to build firmly nonexpansive CNNs. We apply the proposed approach to train a CNN for an image denoising task and show its effectiveness through simulations.