mlsanityData to 7 Oct 2026

Bayesian Inversion for Nonlinear Imaging Models using Deep Generative Priors

arXiv 2203.10078 ↗First posted 18 Mar 2022cs.CV eess.SPcited by 9

Not on the map. Why?

Abstract (arXiv)

Most modern imaging systems incorporate a computational pipeline to infer the image of interest from acquired measurements. The Bayesian approach to solve such ill-posed inverse problems involves the characterization of the posterior distribution of the image. It depends on the model of the imaging system and on prior knowledge on the image of interest. In this work, we present a Bayesian reconstruction framework for nonlinear imaging models where we specify the prior knowledge on the image through a deep generative model. We develop a tractable posterior-sampling scheme based on the Metropolis-adjusted Langevin algorithm for the class of nonlinear inverse problems where the forward model has a neural-network-like structure. This class includes most practical imaging modalities. We introduce the notion of augmented deep generative priors in order to suitably handle the recovery of quantitative images.We illustrate the advantages of our framework by applying it to two nonlinear imaging modalities-phase retrieval and optical diffraction tomography.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 47 of its 105 references that are in the map. First posted on arXiv 18 Mar 2022.

Builds on

47 of 105 references.

References · 47

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2022Generative Adversarial Networkscited by 5,603
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  4. 2013Auto-Encoding Variational Bayescited by 3,980
  5. 2016Improved Techniques for Training GANscited by 2,938
  6. 2017Improved Training of Wasserstein GANscited by 2,223
  7. 2021Solving Inverse Problems in Medical Imaging with Score-Based Generative Modelscited by 514
  8. 2020Plug-and-Play Image Restoration with Deep Denoiser Priorcited by 467
  9. 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 460
  10. 2016Deep Convolutional Neural Network for Inverse Problems in Imagingcited by 431
  11. 2019Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processingcited by 411
  12. 2017MoDL: Model Based Deep Learning Architecture for Inverse Problemscited by 384
35 more
  1. 2017Compressed Sensing using Generative Modelscited by 337
  2. 2016The Little Engine that Could: Regularization by Denoising (RED)cited by 303
  3. 2021Robust Compressed Sensing MRI with Deep Generative Priorscited by 284
  4. 2017Learned Primal-dual Reconstructioncited by 251
  5. 2017Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN)cited by 224
  6. 2019On instabilities of deep learning in image reconstruction - Does AI come at a cost?cited by 211
  7. 2019Plug-and-Play Methods Provably Converge with Properly Trained Denoiserscited by 197
  8. 2015Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restorationcited by 194
  9. 2021SNIPS: Solving Noisy Inverse Problems Stochasticallycited by 191
  10. 2014Phase Retrieval via Wirtinger Flow: Theory and Algorithmscited by 123
  11. 2021Bayesian imaging using Plug & Play priors: when Langevin meets Tweediecited by 96
  12. 2017Deep learning for undersampled MRI reconstructioncited by 91
  13. 2020Solving Linear Inverse Problems Using the Prior Implicit in a Denoisercited by 78
  14. 2017CNN-Based Projected Gradient Descent for Consistent Image Reconstructioncited by 75
  15. 2018Phase Retrieval Under a Generative Priorcited by 73
  16. 2017One Network to Solve Them All --- Solving Linear Inverse Problems using Deep Projection Modelscited by 67
  17. 2019RARE: Image Reconstruction using Deep Priors Learned without Ground Truthcited by 64
  18. 2018Deep Bayesian Inversioncited by 60
  19. 2018Solving Linear Inverse Problems Using GAN Priors: An Algorithm with Provable Guaranteescited by 58
  20. 2020Scalable Plug-and-Play ADMM with Convergence Guaranteescited by 49
  21. 2017Fundamental Limits of Weak Recovery with Applications to Phase Retrievalcited by 39
  22. 2020Convolutional Proximal Neural Networks and Plug-and-Play Algorithmscited by 36
  23. 2019Block Coordinate Regularization by Denoisingcited by 33
  24. 2019Learned reconstructions for practical mask-based lensless imagingcited by 31
  25. 2021Solving Inverse Problems by Joint Posterior Maximization with Autoencoding Priorcited by 24
  26. 2021Bayesian Imaging With Data-Driven Priors Encoded by Neural Networks: Theory, Methods, and Algorithmscited by 24
  27. 2019On the well-posedness of Bayesian inverse problemscited by 20
  28. 2019SIMBA: Scalable Inversion in Optical Tomography using Deep Denoising Priorscited by 16
  29. 2018A Provably Convergent Scheme for Compressive Sensing under Random Generative Priorscited by 15
  30. 2020CNN-Based Image Reconstruction Method for Ultrafast Ultrasound Imagingcited by 9
  31. 2017Efficient Inversion of Multiple-Scattering Model for Optical Diffraction Tomographycited by 6
  32. 2019Bayesian Inference with Generative Adversarial Network Priorscited by 6
  33. 2019Solving Inverse Problems by Joint Posterior Maximization with a VAE Priorcited by 6
  34. 2020Sampling possible reconstructions of undersampled acquisitions in MR imagingcited by 5
  35. 2013Phase retrieval for imaging problemscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 1; 2024: 3; 2025: 3; 2026: 1.

9 papers.

  1. 2022Conditional Injective Flows for Bayesian Imagingcited by 13
  2. 2024Conditional score-based diffusion models for solving inverse problems in mechanicscited by 6
  3. 2023A Comparative Study of Variational Autoencoders, Normalizing Flows, and Score-based Diffusion Models for Electrical Impedance Tomographycited by 4
  4. 2025Conformalized Generative Bayesian Imaging: An Uncertainty Quantification Framework for Computational Imagingcited by 4
  5. 2025How many measurements are enough? Bayesian recovery in inverse problems with general distributionscited by 2
  6. 2026Error Analysis of Bayesian Inverse Problems with Generative Priorscited by 2
  7. 2024Robustness and Exploration of Variational and Machine Learning Approaches to Inverse Problems: An Overviewcited by 1
  8. 2024Integrating Generative and Physics-Based Models for Ptychographic Imaging with Uncertainty Quantificationcited by 1
  9. 2025Breaking the Weak Recovery Limit in Random Phase Retrieval with Learned Regularizerscited by 0