Solving ill-posed inverse problems using iterative deep neural networks
From MaRDI portal
Publication:4601414
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.
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
Cited in
(only showing first 100 items - show all)- scientific article; zbMATH DE number 7306876 (Why is no real title available?)
- On learned operator correction in inverse problems
- Deep unfolding of a proximal interior point method for image restoration
- In focus -- hybrid deep learning approaches to the HDC2021 challenge
- Solving inverse problems using data-driven models
- Solving optical tomography with deep learning
- Linearized inverse Schrödinger potential problem with partial data and its deep neural network inversion
- Inverse problems on low-dimensional manifolds
- Learning and correcting non-Gaussian model errors
- Adversarially learned iterative reconstruction for imaging inverse problems
- Deep learning for trivial inverse problems
- Physics-constrained deep learning for high-dimensional surrogate modeling and uncertainty quantification without labeled data
- 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
- Deep unrolling networks with recurrent momentum acceleration for nonlinear inverse problems
- An efficient algorithm to compute the X-ray transform
- 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
- First arrival traveltime tomography using supervised descent learning technique
- 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
- A physics-informed variational DeepONet for predicting crack path in quasi-brittle materials
- 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
- Approximation spaces of deep neural networks
- 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
- Data-driven nonsmooth optimization
- Deep convolutional framelets: a general deep learning framework 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
- 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)
- Recent trends and advances in solving the inverse problem for EEG source localization
- Training adaptive reconstruction networks for blind inverse problems
- Deep neural networks for inverse problems with pseudodifferential operators: an application to limited-angle tomography
- Model reduction and neural networks for parametric PDEs
- The first 100 years of the Radon transform
- Wasserstein-based projections with applications to 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
- Feasibility-based fixed point networks
- 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
- Equivariant neural networks for inverse problems
- Divide-and-conquer DNN approach for the inverse point source problem using a few single frequency measurements
- Deep neural networks can stably solve high-dimensional, noisy, non-linear inverse problems
- 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
- 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
- Optimization with learning-informed differential equation constraints and its applications
- An introduction to the mathematics of deep learning
- 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
- 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
- Approximation of discontinuous inverse operators with neural networks
- Unsupervised knowledge-transfer for learned image reconstruction
- Projected regression method for solving Fredholm integral equations arising in the analytic continuation problem of quantum physics
- Deep synthesis network for regularizing inverse problems
- Semi-supervised invertible neural operators for Bayesian inverse problems
- Relaxation approach for learning neural network regularizers for a class of identification problems
- Normalizing flow regularization for photoacoustic tomography
- Nonlocal kernel network (NKN): a stable and resolution-independent deep neural network
- Learning the invisible: a hybrid deep learning-shearlet framework for limited angle computed tomography
- Fast Bayesian inversion for high dimensional inverse problems
- The deep arbitrary polynomial chaos neural network or how deep artificial neural networks could benefit from data-driven homogeneous chaos theory
- A surrogate hyperplane Bregman-Kaczmarz method for solving linear inverse problems
- Infinite-dimensional inverse problems with finite measurements
- Compressive sensing and neural networks from a statistical learning perspective
- Inverse problems are solvable on real number signal processing hardware
- Vision graph U-Net: geometric learning enhanced encoder for medical image segmentation and restoration
- Solving traveltime tomography with deep learning
- Computed tomography reconstruction using deep image prior and learned reconstruction methods
- A review on deep learning in medical image reconstruction
- Invertible residual networks in the context of regularization theory for linear inverse problems
- Neural-network-based regularization methods for inverse problems in imaging
- Data driven regularization by projection
- Learnable Douglas-Rachford iteration and its applications in DOT imaging
- An enhanced V-cycle MgNet model for operator learning in numerical partial differential equations
- Data-consistent neural networks for solving nonlinear inverse problems
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)
