Solving ill-posed inverse problems using iterative deep neural networks
From MaRDI portal
Publication:4601414
DOI10.1088/1361-6420/AA9581zbMATH Open1394.92070arXiv1704.04058OpenAlexW3101765447MaRDI QIDQ4601414FDOQ4601414
Authors: Jonas Adler, Ozan Öktem 
Publication date: 16 January 2018
Published in: Inverse Problems (Search for Journal in Brave)
Abstract: We propose a partially learned approach for the solution of ill posed inverse problems with not necessarily linear forward operators. The method builds on ideas from classical regularization theory and recent advances in deep learning to perform learning while making use of prior information about the inverse problem encoded in the forward operator, noise model and a regularizing functional. The method results in a gradient-like iterative scheme, where the "gradient" component is learned using a convolutional network that includes the gradients of the data discrepancy and regularizer as input in each iteration. We present results of such a partially learned gradient scheme on a non-linear tomographic inversion problem with simulated data from both the Sheep-Logan phantom as well as a head CT. The outcome is compared against FBP and TV reconstruction and the proposed method provides a 5.4 dB PSNR improvement over the TV reconstruction while being significantly faster, giving reconstructions of 512 x 512 volumes in about 0.4 seconds using a single GPU.
Full work available at URL: https://arxiv.org/abs/1704.04058
Recommendations
- NETT: solving inverse problems with deep neural networks
- Deep learning for inverse problems with unknown operator
- Big in Japan: regularizing networks for solving inverse problems
- Deep neural networks can stably solve high-dimensional, noisy, non-linear inverse problems
- Learnable Douglas-Rachford iteration and its applications in DOT imaging
Learning and adaptive systems in artificial intelligence (68T05) Biomedical imaging and signal processing (92C55) Numerical solution to inverse problems in abstract spaces (65J22)
Cited In (only showing first 100 items - show all)
- Physics-constrained deep learning for high-dimensional surrogate modeling and uncertainty quantification without labeled data
- Adversarially learned iterative reconstruction for imaging inverse problems
- Big in Japan: regularizing networks for solving inverse problems
- Networks for nonlinear diffusion problems in imaging
- Convergence Rates of Spectral Regularization Methods: A Comparison between Ill-Posed Inverse Problems and Statistical Kernel Learning
- Learning Regularization Parameter-Maps for Variational Image Reconstruction Using Deep Neural Networks and Algorithm Unrolling
- Mini-workshop: Deep learning and inverse problems. Abstracts from the mini-workshop held March 4--10, 2018
- Deep learning architectures for nonlinear operator functions and nonlinear inverse problems
- A physics-informed variational DeepONet for predicting crack path in quasi-brittle materials
- Approximation spaces of deep neural networks
- Data-driven nonsmooth optimization
- Deep convolutional framelets: a general deep learning framework for inverse problems
- Recent trends and advances in solving the inverse problem for EEG source localization
- Determining the defect locations and sizes in elastic plates by using the artificial neural network and boundary element method
- A Helmholtz equation solver using unsupervised learning: application to transcranial ultrasound
- Deep learning for inverse problems. Abstracts from the workshop held March 7--13, 2021 (hybrid meeting)
- Deep neural networks for inverse problems with pseudodifferential operators: an application to limited-angle tomography
- Model reduction and neural networks for parametric PDEs
- Wasserstein-based projections with applications to inverse problems
- The first 100 years of the Radon transform
- Feasibility-based fixed point networks
- Equivariant neural networks for inverse problems
- Deep neural networks can stably solve high-dimensional, noisy, non-linear inverse problems
- Shallow neural networks for fluid flow reconstruction with limited sensors
- Deep null space learning for inverse problems: convergence analysis and rates
- Learning deep implicit Fourier neural operators (IFNOs) with applications to heterogeneous material modeling
- A data and knowledge driven approach for SPECT using convolutional neural networks and iterative algorithms
- Learning phase field mean curvature flows with neural networks
- Deep learning for inverse problems with unknown operator
- Approximation of discontinuous inverse operators with neural networks
- Semi-supervised invertible neural operators for Bayesian inverse problems
- Deep synthesis network for regularizing inverse problems
- Projected regression method for solving Fredholm integral equations arising in the analytic continuation problem of quantum physics
- Learning the invisible: a hybrid deep learning-shearlet framework for limited angle computed tomography
- Nonlocal kernel network (NKN): a stable and resolution-independent deep neural network
- Fast Bayesian inversion for high dimensional inverse problems
- Infinite-dimensional inverse problems with finite measurements
- Compressive sensing and neural networks from a statistical learning perspective
- Computed tomography reconstruction using deep image prior and learned reconstruction methods
- Solving traveltime tomography with deep learning
- Invertible residual networks in the context of regularization theory for linear inverse problems
- A review on deep learning in medical image reconstruction
- Learnable Douglas-Rachford iteration and its applications in DOT imaging
- Data-consistent neural networks for solving nonlinear inverse problems
- Task adapted reconstruction for inverse problems
- Estimating adsorption isotherm parameters in chromatography via a virtual injection promoting double feed-forward neural network
- A Data-Driven Iteratively Regularized Landweber Iteration
- NETT: solving inverse problems with deep neural networks
- Numerical solution of inverse problems by weak adversarial networks
- Solving inverse problems using conditional invertible neural networks
- Title not available (Why is that?)
- Designing rotationally invariant neural networks from PDEs and variational methods
- On learned operator correction in inverse problems
- Deep unfolding of a proximal interior point method for image restoration
- Solving inverse problems using data-driven models
- Solving optical tomography with deep learning
- Inverse problems on low-dimensional manifolds
- Linearized inverse Schrödinger potential problem with partial data and its deep neural network inversion
- Learning and correcting non-Gaussian model errors
- Deep learning for trivial inverse problems
- Deep unrolling networks with recurrent momentum acceleration for nonlinear inverse problems
- An efficient algorithm to compute the X-ray transform
- Gabor-filtered Fourier neural operator for solving partial differential equations
- Learning a stable approximation of an existing but unknown inverse mapping: application to the half-time circular Radon transform
- First arrival traveltime tomography using supervised descent learning technique
- A direct sampling-based deep learning approach for inverse medium scattering problems
- DRIP: deep regularizers for inverse problems
- A Data-Assisted Two-Stage Method for the Inverse Random Source Problem
- An accelerated inexact Newton regularization scheme with a learned feature-selection rule for non-linear inverse problems
- TNet: A Model-Constrained Tikhonov Network Approach for Inverse Problems
- Rethinking the ill-posedness of the spectral function reconstruction -- why is it fundamentally hard and how artificial neural networks can help
- A new approach to solve inverse problems: combination of model-based solving and example-based learning
- Training adaptive reconstruction networks for blind inverse problems
- Gauss-Newton method for solving linear inverse problems with neural network coders
- Neural and spectral operator surrogates: unified construction and expression rate bounds
- On Learning the Invisible in Photoacoustic Tomography with Flat Directionally Sensitive Detector
- PnP-ReG: Learned Regularizing Gradient for Plug-and-Play Gradient Descent
- Reconstruction of inhomogeneous media by an iteration algorithm with a learned projector
- Bilevel optimization methods in imaging
- Deep learning methods for limited data problems in X-ray tomography
- Learned iterative reconstruction
- Learned regularizers for inverse problems
- Regularization of inverse problems by neural networks
- Sparse regularized CT reconstruction: an optimization perspective
- Shearlets: from theory to deep learning
- Divide-and-conquer DNN approach for the inverse point source problem using a few single frequency measurements
- A data-driven Kaczmarz iterative regularization method with non-smooth constraints for ill-posed problems
- Generalized intersection algorithms with fixed points for image decomposition learning
- A neural network warm-start approach for the inverse acoustic obstacle scattering problem
- Application of machine learning regression models to inverse eigenvalue problems
- Optimization with learning-informed differential equation constraints and its applications
- An introduction to the mathematics of deep learning
- Deep unfolding as iterative regularization for imaging inverse problems
- Numerical methods for identifying the diffusion coefficient in a nonlinear elliptic equation
- Solving inverse problems with deep learning
- The mathematics of artificial intelligence
- Unsupervised knowledge-transfer for learned image reconstruction
- Relaxation approach for learning neural network regularizers for a class of identification problems
- Normalizing flow regularization for photoacoustic tomography
- The deep arbitrary polynomial chaos neural network or how deep artificial neural networks could benefit from data-driven homogeneous chaos theory
This page was built for publication: Solving ill-posed inverse problems using iterative deep neural networks
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4601414)
