Data to 7 Oct 2026

A Review of Convolutional Neural Networks for Inverse Problems in Imaging

arXiv 1710.04011 ↗First posted 11 Oct 2017eess.IV cs.CVcited by 81

Not on the map. Why?

Abstract (arXiv)

In this survey paper, we review recent uses of convolution neural networks (CNNs) to solve inverse problems in imaging. It has recently become feasible to train deep CNNs on large databases of images, and they have shown outstanding performance on object classification and segmentation tasks. Motivated by these successes, researchers have begun to apply CNNs to the resolution of inverse problems such as denoising, deconvolution, super-resolution, and medical image reconstruction, and they have started to report improvements over state-of-the-art methods, including sparsity-based techniques such as compressed sensing. Here, we review the recent experimental work in these areas, with a focus on the critical design decisions: Where does the training data come from? What is the architecture of the CNN? and How is the learning problem formulated and solved? We also bring together a few key theoretical papers that offer perspective on why CNNs are appropriate for inverse problems and point to some next steps in the field.

Key facts. Cited by 81 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Oct 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 22; 2022: 13; 2023: 15; 2024: 9; 2025: 11; 2026: 11.

81 papers.

Sort:

By area:

2021SNIPS: Solving Noisy Inverse Problems Stochasticallycited by 191
2021Can stable and accurate neural networks be computed? -- On the barriers of deep learning and Smale's 18th problemcited by 53
2021On Measuring and Controlling the Spectral Bias of the Deep Image Priorcited by 36
2021Two-layer neural networks with values in a Banach spacecited by 26
2023What's in a Prior? Learned Proximal Networks for Inverse Problemscited by 24
2021Recovery Analysis for Plug-and-Play Priors using the Restricted Eigenvalue Conditioncited by 22
2022Online Deep Equilibrium Learning for Regularization by Denoisingcited by 22
2022Theoretical Perspectives on Deep Learning Methods in Inverse Problemscited by 22
2021Learning Regularization Parameters of Inverse Problems via Deep Neural Networkscited by 19
2021SGD-Net: Efficient Model-Based Deep Learning with Theoretical Guaranteescited by 18
2021An Optimization-Based Meta-Learning Model for MRI Reconstruction with Diverse Datasetcited by 18
2021Real-Time Topology Optimization in 3D via Deep Transfer Learningcited by 14

38 more

2021Untrained networks for compressive lensless photographycited by 13
2023Prior Mismatch and Adaptation in PnP-ADMM with a Nonconvex Convergence Analysiscited by 10
2024Blind Inversion using Latent Diffusion Priorscited by 10
2021Scaling Up Bayesian Uncertainty Quantification for Inverse Problems using Deep Neural Networkscited by 9
2021Deformation-Compensated Learning for Image Reconstruction without Ground Truthcited by 9
2022Image-to-Image MLP-mixer for Image Reconstructioncited by 9
2023PtychoDV: Vision Transformer-Based Deep Unrolling Network for Ptychographic Image Reconstructioncited by 9
2022Deep Model-Based Architectures for Inverse Problems under Mismatched Priorscited by 8
2023Block Coordinate Plug-and-Play Methods for Blind Inverse Problemscited by 8
2023Plug-and-Play Posterior Sampling under Mismatched Measurement and Prior Modelscited by 8
2021Reconstructing High-resolution Turbulent Flows Using Physics-Guided Neural Networkscited by 6
2023All-optical image denoising using a diffractive visual processorcited by 6
2024Glimpse: Generalized Locality for Scalable and Robust CTcited by 6
2022NESTANets: Stable, accurate and efficient neural networks for analysis-sparse inverse problemscited by 5
2022CoRRECT: A Deep Unfolding Framework for Motion-Corrected Quantitative R2* Mappingcited by 5
2022Robustness of Deep Equilibrium Architectures to Changes in the Measurement Modelcited by 4
2023A Direct Sampling-Based Deep Learning Approach for Inverse Medium Scattering Problemscited by 4
2023Learning of Sea Surface Height Interpolation from Multi-variate Simulated Satellite Observationscited by 4
2021End-to-End Simultaneous Learning of Single-particle Orientation and 3D Map Reconstruction from Cryo-electron Microscopy Datacited by 3
2021Efficient Hierarchical Bayesian Inference for Spatio-temporal Regression Models in Neuroimagingcited by 3
2022Mining the manifolds of deep generative models for multiple data-consistent solutions of ill-posed tomographic imaging problemscited by 3
2023TRIDENT: The Nonlinear Trilogy for Implicit Neural Representationscited by 3
2023Single-Shot Plug-and-Play Methods for Inverse Problemscited by 3
2024Overcoming Distribution Shifts in Plug-and-Play Methods with Test-Time Trainingcited by 3
2024A Brief Overview of Optimization-Based Algorithms for MRI Reconstruction Using Deep Learningcited by 3
2025UGoDIT: Unsupervised Group Deep Image Prior Via Transferable Weightscited by 3
2021Advancing biological super-resolution microscopy through deep learning: a brief reviewcited by 2
2021Revisit Geophysical Imaging in A New View of Physics-informed Generative Adversarial Learningcited by 2
2022Alternative Data Augmentation for Industrial Monitoring using Adversarial Learningcited by 2
2022Localized adversarial artifacts for compressed sensing MRIcited by 2
2023Convergence analysis of equilibrium methods for inverse problemscited by 2
2023Efficient Model-Based Deep Learning via Network Pruning and Fine-Tuningcited by 2
2023When can you trust feature selection? -- I: A condition-based analysis of LASSO and generalised hardness of approximationcited by 2
2024What is Wrong with End-to-End Learning for Phase Retrieval?cited by 2
2024Parseval Convolution Operators and Neural Networkscited by 2
2024LoFi: Neural Local Fields for Scalable Image Reconstructioncited by 2
2025Plug-and-Play Posterior Sampling for Blind Inverse Problemscited by 2
2026An analytic theory of convolutional neural network inverse problems solverscited by 2

50 most cited of 81 All 81 (JSON)