Constrained and unconstrained deep image prior optimization models with automatic regularization

DOI10.1007/S10589-022-00392-WMaRDI QIDQ2111471zbMATH OpenOpenAlexFDO

Authors Pasquale Cascarano, Giorgia Franchini, Erich Kobler, F. Porta, Andrea Sebastiani

Publication date 16 January 2023

Published in Computational Optimization and Applications (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/s10589-022-00392-w

zbMATH Keywords

image deblurringimage denoisingconvolutional neural networksautomatic regularizationdeep image priorgradient descent-ascent methodsregularization by denoising

Mathematics Subject Classification ID

Numerical optimization and variational techniques (65K10) Convex programming (90C25) Artificial neural networks and deep learning (68T07) Large-scale problems in mathematical programming (90C06) Biomedical imaging and signal processing (92C55) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08) Computing methodologies for image processing (68U10)

Recommendations

• Regularization by architecture: a deep prior approach for inverse problems
• Blind Poissonian image deblurring regularized by a denoiser constraint and deep image prior
• Deep unfolding of a proximal interior point method for image restoration
• The Little Engine that Could: Regularization by Denoising (RED)
• A Generative Variational Model for Inverse Problems in Imaging

Cites work

• scientific article; zbMATH DE number 1194487 (Why is no real title available?)
• A Fast Adaptive Parameter Estimation for Total Variation Image Restoration
• Adaptive parameter selection for total variation image deconvolution
• Analysis of Discrete Ill-Posed Problems by Means of the L-Curve
• Computed tomography reconstruction using deep image prior and learned reconstruction methods
• Deep Convolutional Neural Network for Inverse Problems in Imaging
• Generalized Cross-Validation as a Method for Choosing a Good Ridge Parameter
• Nonlinear total variation based noise removal algorithms
• Numerical methods for parameter estimation in Poisson data inversion
• Regularization by architecture: a deep prior approach for inverse problems
• Solving constrained total-variation image restoration and reconstruction problems via alternating direction methods
• Solving inverse problems using data-driven models
• The Little Engine that Could: Regularization by Denoising (RED)
• UPRE method for total variation parameter selection
• Uniform Penalty inversion of two-dimensional NMR relaxation data
• Variational methods in imaging

Cited in

(4)

• Regularization by architecture: a deep prior approach for inverse problems
• Learning deep optimizer for blind image deconvolution
• Neural blind deconvolution with Poisson data
• Deep unfolding of a proximal interior point method for image restoration

Describes a project that uses

Uses Software

• Noise2Noise
• DeepRED
• compsensing_dip
• Adam

This page was built for publication: Constrained and unconstrained deep image prior optimization models with automatic regularization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2111471)