Regularization by architecture: a deep prior approach for inverse problems
From MaRDI portal
Publication:1988362
DOI10.1007/s10851-019-00923-xzbMath1434.68505arXiv1812.03889OpenAlexW3101558399MaRDI QIDQ1988362
Peter Maass, Sören Dittmer, Tobias Kluth, Daniel Otero Baguer
Publication date: 23 April 2020
Published in: Journal of Mathematical Imaging and Vision (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1812.03889
Artificial neural networks and deep learning (68T07) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08) Numerical solution to inverse problems in abstract spaces (65J22)
Related Items (16)
Regularization theory of the analytic deep prior approach ⋮ A Generative Variational Model for Inverse Problems in Imaging ⋮ A machine learning approach to optimal Tikhonov regularization I: Affine manifolds ⋮ Deep learning methods for partial differential equations and related parameter identification problems ⋮ A variable projection method for large-scale inverse problems with \(\ell^1\) regularization ⋮ Restoring severely out-of-focus blurred text images with deep image prior ⋮ Invertible residual networks in the context of regularization theory for linear inverse problems ⋮ Regularising inverse problems with generative machine learning models ⋮ Computed tomography reconstruction using deep image prior and learned reconstruction methods ⋮ Numerical solution of inverse problems by weak adversarial networks ⋮ Deep synthesis network for regularizing inverse problems ⋮ Learning regularization parameters of inverse problems via deep neural networks ⋮ Solving inverse problems using data-driven models ⋮ Unsupervised knowledge-transfer for learned image reconstruction* ⋮ Constrained and unconstrained deep image prior optimization models with automatic regularization ⋮ Imaging based on Compton scattering: model uncertainty and data-driven reconstruction methods
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
- Lectures on convex optimization
- Deep Learning for Trivial Inverse Problems
- Deep Convolutional Neural Network for Inverse Problems in Imaging
- Tradeoffs Between Convergence Speed and Reconstruction Accuracy in Inverse Problems
- An iterative thresholding algorithm for linear inverse problems with a sparsity constraint
- Multi-Layer Sparse Coding: The Holistic Way
- Neural Simpletrons: Learning in the Limit of Few Labels with Directed Generative Networks
- Solving inverse problems using data-driven models
- Signal Recovery by Proximal Forward-Backward Splitting
This page was built for publication: Regularization by architecture: a deep prior approach for inverse problems
