Deep Null Space Learning for Inverse Problems: Convergence Analysis and Rates

Abstract

Recently, deep learning based methods appeared as a new paradigm for solving inverse problems. These methods empirically show excellent performance but lack of theoretical justification; in particular, no results on the regularization properties are available. In particular, this is the case for two-step deep learning approaches, where a classical reconstruction method is applied to the data in a first step and a trained deep neural network is applied to improve results in a second step. In this paper, we close the gap between practice and theory for a new network structure in a two-step approach. For that purpose, we propose so called null space networks and introduce the concept of M-regularization. Combined with a standard regularization method as reconstruction layer, the proposed deep null space learning approach is shown to be a M-regularization method; convergence rates are also derived. The proposed null space network structure naturally preserves data consistency which is considered as key property of neural networks for solving inverse problems.

References in corpus (2)

• Deep Learning Microscopy
• CNN-Based Projected Gradient Descent for Consistent Image Reconstruction

Cited by in corpus (14)

• Computed Tomography Reconstruction Using Deep Image Prior and Learned Reconstruction Methods
• Learning The Invisible: A Hybrid Deep Learning-Shearlet Framework for Limited Angle Computed Tomography
• Diffusion Models, Image Super-Resolution And Everything: A Survey
• Diffusion Model-Based Image Editing: A Survey
• Neural Networks-based Regularization for Large-Scale Medical Image Reconstruction
• Known Operator Learning and Hybrid Machine Learning in Medical Imaging -- A Review of the Past, the Present, and the Future
• An End-To-End-Trainable Iterative Network Architecture for Accelerated Radial Multi-Coil 2D Cine MR Image Reconstruction
• Data driven regularization by projection
• Big in Japan: Regularizing networks for solving inverse problems
• Physics-assisted Generative Adversarial Network for X-Ray Tomography
• Invertible residual networks in the context of regularization theory for linear inverse problems
• NoSENSE: Learned unrolled cardiac MRI reconstruction without explicit sensitivity maps
• Rotational Augmented Noise2Inverse for Low-dose Computed Tomography Reconstruction
• Learning a Gaussian Mixture for Sparsity Regularization in Inverse Problems