A Generative Variational Model for Inverse Problems in Imaging

DOI10.1137/21M1414978zbMath1485.49042arXiv2104.12630MaRDI QIDQ5065477

Martin Holler, Andreas Habring

Publication date: 21 March 2022

Published in: SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2104.12630

zbMATH Keywords

inverse problemsmachine learningdata sciencedeep image priormathematical imaginggenerative neural networks

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08) Numerical solutions of ill-posed problems in abstract spaces; regularization (65J20) Inverse problems in optimal control (49N45)

Related Items

Regularization theory of the analytic deep prior approach, A Note on the Regularity of Images Generated by Convolutional Neural Networks, Regularising inverse problems with generative machine learning models

Uses Software

• PyCUDA
• PyOpenCL
• GitHub
• convex_learning
• compsensing_dip
• DeepAdverserialRegulariser
• NETT

Cites Work

• Unnamed Item
• Unnamed Item
• Nonlinear total variation based noise removal algorithms
• Variational methods in imaging
• A convex variational model for learning convolutional image atoms from incomplete data
• Regularization by architecture: a deep prior approach for inverse problems
• Mathematical image processing. Translated from the German
• Sparsity of solutions for variational inverse problems with finite-dimensional data
• A Total Variation–Based JPEG Decompression Model
• Secrets of image denoising cuisine
• Inertial Proximal Alternating Linearized Minimization (iPALM) for Nonconvex and Nonsmooth Problems
• Lower semicontinuity and relaxation results in BV for integral functionals with BV integrands
• A function space framework for structural total variation regularization with applications in inverse problems
• Convolutional Sparse and Low-Rank Coding-Based Image Decomposition
• Multi-Layer Convolutional Sparse Modeling: Pursuit and Dictionary Learning
• NETT: solving inverse problems with deep neural networks
• Computed tomography reconstruction using deep image prior and learned reconstruction methods
• Higher-order total variation approaches and generalisations
• Deep synthesis network for regularizing inverse problems
• Sample-Efficient Algorithms for Recovering Structured Signals From Magnitude-Only Measurements
• Solving inverse problems using data-driven models
• On Representer Theorems and Convex Regularization
• A convergence rates result for Tikhonov regularization in Banach spaces with non-smooth operators
• Total Generalized Variation