Constrained and unconstrained deep image prior optimization models with automatic regularization

DOI10.1007/s10589-022-00392-wOpenAlexW4288724477MaRDI QIDQ2111471

Giorgia Franchini, Pasquale Cascarano, Andrea Sebastiani, Federica Porta, Erich Kobler

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 denoisingimage deblurringconvolutional neural networksautomatic regularizationdeep image priorgradient descent-ascent methodsregularization by denoising

Mathematics Subject Classification ID

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

Related Items

Neural blind deconvolution with Poisson data

Uses Software

• Adam
• compsensing_dip
• DeepRED
• Noise2Noise

Cites Work

• Unnamed Item
• Nonlinear total variation based noise removal algorithms
• The Little Engine that Could: Regularization by Denoising (RED)
• Numerical methods for parameter estimation in Poisson data inversion
• Variational methods in imaging
• UPRE method for total variation parameter selection
• Regularization by architecture: a deep prior approach for inverse problems
• Uniform Penalty inversion of two-dimensional NMR relaxation data
• Solving Constrained Total-variation Image Restoration and Reconstruction Problems via Alternating Direction Methods
• Adaptive Parameter Selection for Total Variation Image Deconvolution
• Generalized Cross-Validation as a Method for Choosing a Good Ridge Parameter
• Analysis of Discrete Ill-Posed Problems by Means of the L-Curve
• A Fast Adaptive Parameter Estimation for Total Variation Image Restoration
• Deep Convolutional Neural Network for Inverse Problems in Imaging
• Computed tomography reconstruction using deep image prior and learned reconstruction methods
• Solving inverse problems using data-driven models