Deep synthesis network for regularizing inverse problems

DOI10.1088/1361-6420/abc7cdOpenAlexW3097913109MaRDI QIDQ5150821

Markus Haltmeier, Daniel Obmann, Johannes Schwab

Publication date: 15 February 2021

Published in: Inverse Problems (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2002.00155

zbMATH Keywords

inverse problemssparsitysparse regularizationdeep learningdeep synthesis regularization

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Numerical analysis (65-XX)

Related Items (6)

Uniformly convex neural networks and non-stationary iterated network Tikhonov (iNETT) method ⋮ Deep Learning--Based Dictionary Learning and Tomographic Image Reconstruction ⋮ A Generative Variational Model for Inverse Problems in Imaging ⋮ Gauss-Newton method for solving linear inverse problems with neural network coders ⋮ A Note on the Regularity of Images Generated by Convolutional Neural Networks ⋮ Quadratic Neural Networks for Solving Inverse Problems

Uses Software

• Adam
• ODL
• DeepAdverserialRegulariser
• NETT

Cites Work

• Unnamed Item
• Unnamed Item
• The Little Engine that Could: Regularization by Denoising (RED)
• A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
• An extension of the variational inequality approach for obtaining convergence rates in regularization of nonlinear ill-posed problems
• Variational methods in imaging
• The Radon transform.
• A first-order primal-dual algorithm for convex problems with applications to imaging
• X-ray CT image reconstruction via wavelet frame based regularization and Radon domain inpainting
• Regularization by architecture: a deep prior approach for inverse problems
• On the interplay of source conditions and variational inequalities for nonlinear ill-posed problems
• Necessary and sufficient conditions for linear convergence of ℓ1-regularization
• Sparse regularization with l ^q penalty term
• Stable Signal Reconstruction via $\ell^1$-Minimization in Redundant, Non-Tight Frames
• Solving ill-posed inverse problems using iterative deep neural networks
• Deep Convolutional Neural Network for Inverse Problems in Imaging
• Convergence rates of convex variational regularization
• Sparse Regularization of Inverse Problems by Operator-Adapted Frame Thresholding
• NETT: solving inverse problems with deep neural networks
• Analysis versus synthesis in signal priors
• A variational formulation for frame-based inverse problems

This page was built for publication: Deep synthesis network for regularizing inverse problems