Deep unfolding of a proximal interior point method for image restoration
From MaRDI portal
Publication:5220306
DOI10.1088/1361-6420/AB460AzbMATH Open1452.94003arXiv1812.04276OpenAlexW2905472194WikidataQ113091821 ScholiaQ113091821MaRDI QIDQ5220306FDOQ5220306
Authors: Carla Bertocchi, E. Chouzenoux, Marie-Caroline Corbineau, M. Prato, Jean-Christophe Pesquet 
Publication date: 16 March 2020
Published in: Inverse Problems (Search for Journal in Brave)
Abstract: Variational methods are widely applied to ill-posed inverse problems for they have the ability to embed prior knowledge about the solution. However, the level of performance of these methods significantly depends on a set of parameters, which can be estimated through computationally expensive and time-consuming methods. In contrast, deep learning offers very generic and efficient architectures, at the expense of explainability, since it is often used as a black-box, without any fine control over its output. Deep unfolding provides a convenient approach to combine variational-based and deep learning approaches. Starting from a variational formulation for image restoration, we develop iRestNet, a neural network architecture obtained by unfolding a proximal interior point algorithm. Hard constraints, encoding desirable properties for the restored image, are incorporated into the network thanks to a logarithmic barrier, while the barrier parameter, the stepsize, and the penalization weight are learned by the network. We derive explicit expressions for the gradient of the proximity operator for various choices of constraints, which allows training iRestNet with gradient descent and backpropagation. In addition, we provide theoretical results regarding the stability of the network for a common inverse problem example. Numerical experiments on image deblurring problems show that the proposed approach compares favorably with both state-of-the-art variational and machine learning methods in terms of image quality.
Full work available at URL: https://arxiv.org/abs/1812.04276
Recommendations
- Learning maximally monotone operators for image recovery
- Variational networks: an optimal control approach to early stopping variational methods for image restoration
- A Generative Variational Model for Inverse Problems in Imaging
- Constrained and unconstrained deep image prior optimization models with automatic regularization
- Solving ill-posed inverse problems using iterative deep neural networks
Convex programming (90C25) Interior-point methods (90C51) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08) Numerical solution to inverse problems in abstract spaces (65J22)
Cites Work
- Distributed optimization and statistical learning via the alternating direction method of multipliers
- Title not available (Why is that?)
- An Inverse Matrix Adjustment Arising in Discriminant Analysis
- On early stopping in gradient descent learning
- Deep learning
- Proximal splitting methods in signal processing
- Signal Recovery by Proximal Forward-Backward Splitting
- Implicit Functions and Solution Mappings
- Computational Methods for Inverse Problems
- Stein Unbiased GrAdient estimator of the Risk (SUGAR) for Multiple Parameter Selection
- Stability of the minimizers of least squares with a non-convex regularization. I: Local behavior
- Title not available (Why is that?)
- Convex analysis and monotone operator theory in Hilbert spaces
- Epigraphical projection for solving least squares Anscombe transformed constrained optimization problems
- The use of Morozov's discrepancy principle for Tikhonov regularization for solving nonlinear ill-posed problems
- Topology preserving deformable image matching using constrained hierarchical parametric models
- A variational formulation for frame-based inverse problems
- Some first-order algorithms for total variation based image restoration
- Non-negatively constrained image deblurring with an inexact interior point method
- Proximal methods in view of interior-point strategies
- On the convergence properties of the projected gradient method for convex optimization
- Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
- Deep Convolutional Neural Network for Inverse Problems in Imaging
- Splitting forward-backward penalty scheme for constrained variational problems
- New convergence results for the scaled gradient projection method
- Title not available (Why is that?)
- Color Image Denoising via Discriminatively Learned Iterative Shrinkage
- An Interior Point Recurrent Neural Network for Convex Optimization Problems
Cited In (18)
- Variational models for signal processing with graph neural networks
- Variational networks: an optimal control approach to early stopping variational methods for image restoration
- Learning Regularization Parameter-Maps for Variational Image Reconstruction Using Deep Neural Networks and Algorithm Unrolling
- Constrained and unconstrained deep image prior optimization models with automatic regularization
- Temporal deep unfolding for constrained nonlinear stochastic optimal control
- Explainable bilevel optimization: an application to the Helsinki Deblur Challenge
- Data-driven nonsmooth optimization
- Learning maximally monotone operators for image recovery
- Marginal likelihood estimation in semiblind image deconvolution: a stochastic approximation approach
- Bregman methods for large-scale optimization with applications in imaging
- Strengthened splitting methods for computing resolvents
- Uniformly convex neural networks and non-stationary iterated network Tikhonov (iNETT) method
- Deep unfolding as iterative regularization for imaging inverse problems
- Solution of mismatched monotone+Lipschitz inclusion problems
- Edge adaptive hybrid regularization model for image deblurring
- Heuristic computing with sequential quadratic programming for solving a nonlinear hepatitis B virus model
- Lipschitz Certificates for Layered Network Structures Driven by Averaged Activation Operators
- Applying smoothing technique and semi-proximal ADMM for image deblurring
Uses Software
This page was built for publication: Deep unfolding of a proximal interior point method for image restoration
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5220306)
