mlsanityData to 7 Oct 2026

Robust Compressed Sensing MRI with Deep Generative Priors

arXiv 2108.01368 ↗First posted 3 Aug 2021cs.LG cs.CV cs.ITcited by 284

Not on the map. Why?

Cited by 169 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

The CSGM framework (Bora-Jalal-Price-Dimakis'17) has shown that deep generative priors can be powerful tools for solving inverse problems. However, to date this framework has been empirically successful only on certain datasets (for example, human faces and MNIST digits), and it is known to perform poorly on out-of-distribution samples. In this paper, we present the first successful application of the CSGM framework on clinical MRI data. We train a generative prior on brain scans from the fastMRI dataset, and show that posterior sampling via Langevin dynamics achieves high quality reconstructions. Furthermore, our experiments and theory show that posterior sampling is robust to changes in the ground-truth distribution and measurement process. Our code and models are available at: urlhttps://github.com/utcsilab/csgm-mri-langevin.

Key facts. Cited by 284 papers in the map (data through 7 Oct 2026). Builds on 49 of its 96 references that are in the map. First posted on arXiv 3 Aug 2021.

Builds on

49 of 96 references.

References · 49

  1. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  3. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  4. 2013Auto-Encoding Variational Bayescited by 3,980
  5. 2017Deep Image Priorcited by 1,097
  6. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,036
  7. 2017Wasserstein GANcited by 635
  8. 2018fastMRI: An Open Dataset and Benchmarks for Accelerated MRIcited by 464
  9. 2016RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentationcited by 463
  10. 2016Deep Convolutional Neural Network for Inverse Problems in Imagingcited by 431
  11. 2017MoDL: Model Based Deep Learning Architecture for Inverse Problemscited by 384
  12. 2017Learning a Variational Network for Reconstruction of Accelerated MRI Datacited by 340
37 more
  1. 2017Compressed Sensing using Generative Modelscited by 337
  2. 2020Deep Learning Techniques for Inverse Problems in Imagingcited by 290
  3. 2017A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstructioncited by 231
  4. 2019On instabilities of deep learning in image reconstruction - Does AI come at a cost?cited by 211
  5. 2020End-to-End Variational Networks for Accelerated MRI Reconstructioncited by 201
  6. 2018Deep Decoder: Concise Image Representations from Untrained Non-convolutional Networkscited by 120
  7. 2019Invertible generative models for inverse problems: mitigating representation error and dataset biascited by 93
  8. 2018Phase Retrieval Under a Generative Priorcited by 73
  9. 2021Intermediate Layer Optimization for Inverse Problems using Deep Generative Modelscited by 70
  10. 2017One Network to Solve Them All --- Solving Linear Inverse Problems using Deep Projection Modelscited by 67
  11. 2021Measuring Robustness in Deep Learning Based Compressive Sensingcited by 53
  12. 2019Uncertainty Quantification in Deep MRI Reconstructioncited by 49
  13. 2019GrappaNet: Combining Parallel Imaging with Deep Learning for Multi-Coil MRI Reconstructioncited by 45
  14. 2021Instance-Optimal Compressed Sensing via Posterior Samplingcited by 43
  15. 2020Compressive sensing with un-trained neural networks: Gradient descent finds the smoothest approximationcited by 39
  16. 2017Global Guarantees for Enforcing Deep Generative Priors by Empirical Riskcited by 37
  17. 2019Image-Adaptive GAN based Reconstructioncited by 36
  18. 2018Modeling Sparse Deviations for Compressed Sensing using Generative Modelscited by 33
  19. 2019Inverting Deep Generative models, One layer at a timecited by 33
  20. 2020Robust Compressed Sensing using Generative Modelscited by 33
  21. 2020High Dimensional Channel Estimation Using Deep Generative Networkscited by 33
  22. 2021Fairness for Image Generation with Uncertain Sensitive Attributescited by 31
  23. 2019Information-Theoretic Lower Bounds for Compressive Sensing with Generative Modelscited by 25
  24. 2020Unsupervised MRI Reconstruction with Generative Adversarial Networkscited by 24
  25. 2020Sample Complexity Bounds for 1-bit Compressive Sensing and Binary Stable Embeddings with Generative Priorscited by 21
  26. 2020Compressible Latent-Space Invertible Networks for Generative Model-Constrained Image Reconstructioncited by 19
  27. 2021Prior Image-Constrained Reconstruction using Style-Based Generative Modelscited by 19
  28. 2019Fast and Provable ADMM for Learning with Generative Priorscited by 18
  29. 2018Task-Aware Compressed Sensing with Generative Adversarial Networkscited by 17
  30. 2019Inference with Deep Generative Priors in High Dimensionscited by 17
  31. 2017Deep Generative Adversarial Networks for Compressed Sensing Automates MRIcited by 15
  32. 2017Inference in Deep Networks in High Dimensionscited by 12
  33. 2019Global Guarantees for Blind Demodulation with Generative Priorscited by 11
  34. 2019Transform Learning for Magnetic Resonance Image Reconstruction: From Model-based Learning to Building Neural Networkscited by 9
  35. 2018Algorithmic Aspects of Inverse Problems Using Generative Modelscited by 8
  36. 2019Robust One-Bit Recovery via ReLU Generative Networks: Near-Optimal Statistical Rate and Global Landscape Analysiscited by 8
  37. 2019Lower Bounds for Compressed Sensing with Generative Modelscited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 44; 2023: 66; 2024: 83; 2025: 56; 2026: 27.

284 papers.

Sort:

By area:

  1. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,375
  2. 2022Denoising Diffusion Restoration Modelscited by 951
  3. 2021Solving Inverse Problems in Medical Imaging with Score-Based Generative Modelscited by 514
  4. 2021Score-based diffusion models for accelerated MRIcited by 308
  5. 2021Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contractioncited by 306
  6. 2022Diffusion Models for Medical Image Analysis: A Comprehensive Surveycited by 269
  7. 2021Deblurring via Stochastic Refinementcited by 248
  8. 2022A Survey on Generative Diffusion Modelcited by 238
  9. 2023A Variational Perspective on Solving Inverse Problems with Diffusion Modelscited by 217
  10. 2022Unsupervised Medical Image Translation with Adversarial Diffusion Modelscited by 191
  11. 2023Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistencycited by 180
  12. 2024A Survey on Diffusion Models for Inverse Problemscited by 173
38 more
  1. 2022Generative Modelling With Inverse Heat Dissipationcited by 164
  2. 2023Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restorationcited by 164
  3. 2024Improving Diffusion Inverse Problem Solving with Decoupled Noise Annealingcited by 157
  4. 2023Solving Linear Inverse Problems Provably via Posterior Sampling with Latent Diffusion Modelscited by 156
  5. 2022Solving 3D Inverse Problems using Pre-trained 2D Diffusion Modelscited by 130
  6. 2023Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse Problemscited by 129
  7. 2023Score-Based Diffusion Models as Principled Priors for Inverse Imagingcited by 126
  8. 2022Adaptive Diffusion Priors for Accelerated MRI Reconstructioncited by 117
  9. 2022Parallel Diffusion Models of Operator and Image for Blind Inverse Problemscited by 113
  10. 2023Ambient Diffusion: Learning Clean Distributions from Corrupted Datacited by 108
  11. 2022Soft Diffusion: Score Matching for General Corruptionscited by 101
  12. 2022Exploring Chemical Space with Score-based Out-of-distribution Generationcited by 95
  13. 2024Principled Probabilistic Imaging using Diffusion Models as Plug-and-Play Priorscited by 93
  14. 2023Beyond First-Order Tweedie: Solving Inverse Problems using Latent Diffusioncited by 78
  15. 2023Restoration-Degradation Beyond Linear Diffusions: A Non-Asymptotic Analysis For DDIM-Type Samplerscited by 73
  16. 2024Diffusion Models in Low-Level Vision: A Surveycited by 73
  17. 2024All-in-one simulation-based inferencecited by 71
  18. 2023Training-free Linear Image Inverses via Flowscited by 70
  19. 2025InverseBench: Benchmarking Plug-and-Play Diffusion Priors for Inverse Problems in Physical Sciencescited by 67
  20. 2022MR Image Denoising and Super-Resolution Using Regularized Reverse Diffusioncited by 66
  21. 2022Measurement-conditioned Denoising Diffusion Probabilistic Model for Under-sampled Medical Image Reconstructioncited by 64
  22. 2024Learning Diffusion Priors from Observations by Expectation Maximizationcited by 60
  23. 2022Diffusion Model Based Posterior Sampling for Noisy Linear Inverse Problemscited by 58
  24. 2023Consistent Diffusion Models: Mitigating Sampling Drift by Learning to be Consistentcited by 58
  25. 2022PET image denoising based on denoising diffusion probabilistic modelscited by 57
  26. 2023Enhancing Deep Reinforcement Learning: A Tutorial on Generative Diffusion Models in Network Optimizationcited by 56
  27. 2022ReconFormer: Accelerated MRI Reconstruction Using Recurrent Transformercited by 52
  28. 2023Provable Probabilistic Imaging using Score-Based Generative Priorscited by 51
  29. 2022MIMO Channel Estimation using Score-Based Generative Modelscited by 50
  30. 2022Sequential Neural Score Estimation: Likelihood-Free Inference with Conditional Score Based Diffusion Modelscited by 50
  31. 2022Bayesian MRI Reconstruction with Joint Uncertainty Estimation using Diffusion Modelscited by 46
  32. 2022JPEG Artifact Correction using Denoising Diffusion Restoration Modelscited by 45
  33. 2024DEFT: Efficient Fine-Tuning of Diffusion Models by Learning the Generalised h-transformcited by 44
  34. 2022Deep Equilibrium Approaches to Diffusion Modelscited by 42
  35. 2022High-Frequency Space Diffusion Models for Accelerated MRIcited by 41
  36. 2023Solving Inverse Problems with Score-Based Generative Priors learned from Noisy Datacited by 40
  37. 2023GSURE-Based Diffusion Model Training with Corrupted Datacited by 40
  38. 2023A Theoretical Justification for Image Inpainting using Denoising Diffusion Probabilistic Modelscited by 37

50 most cited of 284 All 284 (JSON)