Deep Learning Techniques for Inverse Problems in Imaging

Abstract

Recent work in machine learning shows that deep neural networks can be used to solve a wide variety of inverse problems arising in computational imaging. We explore the central prevailing themes of this emerging area and present a taxonomy that can be used to categorize different problems and reconstruction methods. Our taxonomy is organized along two central axes: (1) whether or not a forward model is known and to what extent it is used in training and testing, and (2) whether or not the learning is supervised or unsupervised, i.e., whether or not the training relies on access to matched ground truth image and measurement pairs. We also discuss the trade-offs associated with these different reconstruction approaches, caveats and common failure modes, plus open problems and avenues for future work.

References in corpus (41)

• Adam: A Method for Stochastic Optimization
• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Deep Convolutional Neural Network for Inverse Problems in Imaging
• Message Passing Algorithms for Compressed Sensing
• Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
• Image reconstruction by domain transform manifold learning
• Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration
• Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections
• On instabilities of deep learning in image reconstruction - Does AI come at a cost?
• Deep-STORM: super-resolution single-molecule microscopy by deep learning
• Compressed Sensing MRI Reconstruction using a Generative Adversarial Network with a Cyclic Loss
• AMP-Inspired Deep Networks for Sparse Linear Inverse Problems
• Generalized SURE for Exponential Families: Applications to Regularization
• Learned D-AMP: Principled Neural Network based Compressive Image Recovery
• Deep Decoder: Concise Image Representations from Untrained Non-convolutional Networks
• Compressed Sensing with Deep Image Prior and Learned Regularization
• Deep Generative Adversarial Networks for Compressed Sensing Automates MRI
• Learning Deep CNN Denoiser Prior for Image Restoration
• Unsupervised Medical Image Translation Using Cycle-MedGAN
• Deep Bayesian Inversion
• One Network to Solve Them All --- Solving Linear Inverse Problems using Deep Projection Models
• Algorithmic Guarantees for Inverse Imaging with Untrained Network Priors
• Denoising and Regularization via Exploiting the Structural Bias of Convolutional Generators
• Unsupervised Learning with Stein's Unbiased Risk Estimator
• Conditional density estimation in a regression setting
• Convolutional neural networks that teach microscopes how to image
• Correction by Projection: Denoising Images with Generative Adversarial Networks
• Learning to See in the Dark
• Learning to Invert: Signal Recovery via Deep Convolutional Networks
• Learning Sensor Multiplexing Design through Back-propagation
• Training Deep Learning Based Denoisers without Ground Truth Data
• An Unsupervised Approach to Solving Inverse Problems using Generative Adversarial Networks
• Deep Optics for Monocular Depth Estimation and 3D Object Detection
• Phase Retrieval Under a Generative Prior
• Exact asymptotics for phase retrieval and compressed sensing with random generative priors
• Solving Linear Inverse Problems Using GAN Priors: An Algorithm with Provable Guarantees
• Global Guarantees for Blind Demodulation with Generative Priors
• Lower Bounds for Compressed Sensing with Generative Models
• Inverting Deep Generative models, One layer at a time
• Data-Driven Design for Fourier Ptychographic Microscopy

Cited by in corpus (6)

• Robust Compressed Sensing MRI with Deep Generative Priors
• Fast ultrasonic imaging using end-to-end deep learning
• Deep Neural Networks Are Effective At Learning High-Dimensional Hilbert-Valued Functions From Limited Data
• Scalable Plug-and-Play ADMM with Convergence Guarantees
• Constant-Expansion Suffices for Compressed Sensing with Generative Priors
• How to do Physics-based Learning