A Generative Variational Model for Inverse Problems in Imaging
From MaRDI portal
Publication:5065477
Abstract: This paper is concerned with the development, analysis and numerical realization of a novel variational model for the regularization of inverse problems in imaging. The proposed model is inspired by the architecture of generative convolutional neural networks; it aims to generate the unknown from variables in a latent space via multi-layer convolutions and non-linear penalties, and penalizes an associated cost. In contrast to conventional neural-network-based approaches, however, the convolution kernels are learned directly from the measured data such that no training is required. The present work provides a mathematical analysis of the proposed model in a function space setting, including proofs for regularity and existence/stability of solutions, and convergence for vanishing noise. Moreover, in a discretized setting, a numerical algorithm for solving various types of inverse problems with the proposed model is derived. Numerical results are provided for applications in inpainting, denoising, deblurring under noise, super-resolution and JPEG decompression with multiple test images.
Recommendations
- Variational inference for computational imaging inverse problems
- Deep Generative Models and Inverse Problems
- Solving Bayesian inverse problems from the perspective of deep generative networks
- Bayesian multiscale deep generative model for the solution of high-dimensional inverse problems
- VI-DGP: a variational inference method with deep generative prior for solving high-dimensional inverse problems
- Adversarially learned iterative reconstruction for imaging inverse problems
- Variational models for image inpainting
- Solution of physics-based Bayesian inverse problems with deep generative priors
- Bilevel approaches for learning of variational imaging models
- Variational regularization in inverse problems and machine learning
Cites work
- scientific article; zbMATH DE number 1448982 (Why is no real title available?)
- A convergence rates result for Tikhonov regularization in Banach spaces with non-smooth operators
- A convex variational model for learning convolutional image atoms from incomplete data
- A function space framework for structural total variation regularization with applications in inverse problems
- A total variation-based JPEG decompression model
- A wavelet tour of signal processing. The sparse way.
- Computed tomography reconstruction using deep image prior and learned reconstruction methods
- Convolutional Sparse and Low-Rank Coding-Based Image Decomposition
- Deep synthesis network for regularizing inverse problems
- Higher-order total variation approaches and generalisations
- Inertial proximal alternating linearized minimization (iPALM) for nonconvex and nonsmooth problems
- Lower semicontinuity and relaxation results in BV for integral functionals with BV integrands
- Mathematical image processing. Translated from the German
- Multi-Layer Convolutional Sparse Modeling: Pursuit and Dictionary Learning
- NETT: solving inverse problems with deep neural networks
- Nonlinear total variation based noise removal algorithms
- On representer theorems and convex regularization
- Regularization by architecture: a deep prior approach for inverse problems
- Sample-Efficient Algorithms for Recovering Structured Signals From Magnitude-Only Measurements
- Secrets of image denoising cuisine
- Solving inverse problems using data-driven models
- Sparsity of solutions for variational inverse problems with finite-dimensional data
- Total generalized variation
- Variational methods in imaging
Cited in
(18)- Solving Inverse Problems by Joint Posterior Maximization with Autoencoding Prior
- Blind image inpainting with sparse directional filter dictionaries for lightweight CNNs
- Multi-layer state evolution under random convolutional design
- Continuous Generative Neural Networks: A Wavelet-Based Architecture in Function Spaces
- Generative modeling of convolutional neural networks
- Learning maximally monotone operators for image recovery
- A convex variational model for learning convolutional image atoms from incomplete data
- Adversarially learned iterative reconstruction for imaging inverse problems
- Variational networks: an optimal control approach to early stopping variational methods for image restoration
- Deep unfolding of a proximal interior point method for image restoration
- Constrained and unconstrained deep image prior optimization models with automatic regularization
- Regularization theory of the analytic deep prior approach
- Deep Generative Models and Inverse Problems
- A Note on the Regularity of Images Generated by Convolutional Neural Networks
- Neural-network-based regularization methods for inverse problems in imaging
- Regularising inverse problems with generative machine learning models
- Robustness and exploration of variational and machine learning approaches to inverse problems: an overview
- Bilevel inverse problems in neuromorphic imaging
Describes a project that uses
Uses Software
This page was built for publication: A Generative Variational Model for Inverse Problems in Imaging
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5065477)
