mlsanityData to 7 Oct 2026

A Stability Benchmark of Generative Regularizers for Inverse Problems

arXiv 2605.10076 ↗First posted 11 May 2026eess.IV cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Generative (diffusion) priors demonstrate remarkable performance in addressing inverse problems in imaging. Yet, for scientific and medical imaging, it is crucial that reconstruction techniques remain stable and reliable under imperfect settings. Typical definitions of stability encompass the notion of ''convergent regularization'', robustness to out-of-distribution data, and to inaccuracies in the forward operator or noise model. We evaluate these properties numerically. Furthermore, we benchmark generative approaches against modern optimization-based methods inspired by the widely used variational techniques. Our results give insights for which settings and applications generative priors can deliver state-of-the-art reconstructions, and on those in which they fall short or may even be problematic.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 61 of its 89 references that are in the map. First posted on arXiv 11 May 2026.

Builds on

61 of 89 references.

References · 61

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2020Denoising Diffusion Implicit Modelscited by 9,655
  4. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  5. 2022Flow Matching for Generative Modelingcited by 5,426
  6. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  7. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  8. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  9. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  10. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,375
  11. 2017Deep Image Priorcited by 1,097
  12. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,095
38 more
  1. 2022Building Normalizing Flows with Stochastic Interpolantscited by 964
  2. 2022Denoising Diffusion Restoration Modelscited by 951
  3. 2022Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Modelcited by 574
  4. 2021Solving Inverse Problems in Medical Imaging with Score-Based Generative Modelscited by 514
  5. 2020Plug-and-Play Image Restoration with Deep Denoiser Priorcited by 467
  6. 2017Compressed Sensing using Generative Modelscited by 337
  7. 2023Denoising Diffusion Models for Plug-and-Play Image Restorationcited by 335
  8. 2016The Little Engine that Could: Regularization by Denoising (RED)cited by 303
  9. 2024Flow Matching Guide and Codecited by 291
  10. 2020Deep Learning Techniques for Inverse Problems in Imagingcited by 290
  11. 2020Bilevel Optimization: Convergence Analysis and Enhanced Designcited by 219
  12. 2023A Variational Perspective on Solving Inverse Problems with Diffusion Modelscited by 217
  13. 2024A Survey on Diffusion Models for Inverse Problemscited by 173
  14. 2024D-Flow: Differentiating through Flows for Controlled Generationcited by 115
  15. 2021Gradient Step Denoiser for convergent Plug-and-Playcited by 107
  16. 2022Plug-and-Play Methods for Integrating Physical and Learned Models in Computational Imagingcited by 94
  17. 2024Principled Probabilistic Imaging using Diffusion Models as Plug-and-Play Priorscited by 93
  18. 2024PnP-Flow: Plug-and-Play Image Restoration with Flow Matchingcited by 92
  19. 2024Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstructioncited by 73
  20. 2025InverseBench: Benchmarking Plug-and-Play Diffusion Priors for Inverse Problems in Physical Sciencescited by 67
  21. 2025FlowDPS: Flow-Driven Posterior Sampling for Inverse Problemscited by 65
  22. 2024DMPlug: A Plug-in Method for Solving Inverse Problems with Diffusion Modelscited by 60
  23. 2020Solving Inverse Problems With Deep Neural Networks -- Robustness Included?cited by 58
  24. 2021Early Stopping for Deep Image Priorcited by 44
  25. 2024DEFT: Efficient Fine-Tuning of Diffusion Models by Learning the Generalised h-transformcited by 44
  26. 2020The troublesome kernel -- On hallucinations, no free lunches and the accuracy-stability trade-off in inverse problemscited by 40
  27. 2023Learning Weakly Convex Regularizers for Convergent Image-Reconstruction Algorithmscited by 30
  28. 2024Blind Image Restoration via Fast Diffusion Inversioncited by 29
  29. 2025DeepInverse: A Python package for solving imaging inverse problems with deep learningcited by 27
  30. 2025Flower: A Flow-Matching Solver for Inverse Problemscited by 23
  31. 2021Regularising Inverse Problems with Generative Machine Learning Modelscited by 22
  32. 2023Score-Based Generative Models for PET Image Reconstructioncited by 22
  33. 2019A Cone-Beam X-Ray CT Data Collection designed for Machine Learningcited by 21
  34. 2021An Educated Warm Start For Deep Image Prior-Based Micro CT Reconstructioncited by 16
  35. 2025Solving Inverse Problems with FLAIRcited by 16
  36. 2023Deep Equilibrium Learning of Explicit Regularizers for Imaging Inverse Problemscited by 15
  37. 2023Neural-network-based regularization methods for inverse problems in imagingcited by 14
  38. 2023Convergent regularization in inverse problems and linear plug-and-play denoiserscited by 13

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Multilevel Stochastic Plug-and-Play for Sparse-View CT Reconstructioncited by 0