mlsanityData to 14 Oct 2026

InverseBench: Benchmarking Plug-and-Play Diffusion Priors for Inverse Problems in Physical Sciences

arXiv 2503.11043 ↗First posted 14 Mar 2025cs.LGcited by 68

On the map: Diffusion models → Inverse problems and image restoration

Abstract (arXiv)

Plug-and-play diffusion priors (PnPDP) have emerged as a promising research direction for solving inverse problems. However, current studies primarily focus on natural image restoration, leaving the performance of these algorithms in scientific inverse problems largely unexplored. To address this gap, we introduce textscInverseBench, a framework that evaluates diffusion models across five distinct scientific inverse problems. These problems present unique structural challenges that differ from existing benchmarks, arising from critical scientific applications such as optical tomography, medical imaging, black hole imaging, seismology, and fluid dynamics. With textscInverseBench, we benchmark 14 inverse problem algorithms that use plug-and-play diffusion priors against strong, domain-specific baselines, offering valuable new insights into the strengths and weaknesses of existing algorithms. To facilitate further research and development, we open-source the codebase, along with datasets and pre-trained models, at https://devzhk.github.io/InverseBench/.

Key facts. Cited by 68 papers in the map (data through 14 Oct 2026). Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models. Builds on 65 of its 130 references that are in the map. First posted on arXiv 14 Mar 2025.

Builds on

65 of 130 references.

Closest ancestors · 13

Same direction, newest first

  1. 2024Ensemble Kalman Diffusion Guidance: A Derivative-free Method for Inverse Problems30 Sep
  2. 2024Improving Diffusion Inverse Problem Solving with Decoupled Noise Annealing1 Jul
  3. 2024Principled Probabilistic Imaging using Diffusion Models as Plug-and-Play Priors29 May
  4. 2024Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstruction25 Mar
  5. 2023Variational Bayesian Imaging with an Efficient Surrogate Score-based Prior5 Sep
  6. 2023Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency16 Jul
  7. 2023Solving Linear Inverse Problems Provably via Posterior Sampling with Latent Diffusion Models2 Jul
  8. 2023Denoising Diffusion Models for Plug-and-Play Image Restoration15 May
  9. 2023A Variational Perspective on Solving Inverse Problems with Diffusion Models7 May
  10. 2023Score-Based Diffusion Models as Principled Priors for Inverse Imaging23 Apr
  11. 2022Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model1 Dec
  12. 2022Diffusion Posterior Sampling for General Noisy Inverse Problems29 Sep
1 more
  1. 2022Denoising Diffusion Restoration Models27 Jan

Other references · 52

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  6. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  7. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  8. 2016Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimizationcited by 699
  9. 2021Physics-Informed Neural Operator for Learning Partial Differential Equationscited by 527
  10. 2021Solving Inverse Problems in Medical Imaging with Score-Based Generative Modelscited by 521
  11. 2018fastMRI: An Open Dataset and Benchmarks for Accelerated MRIcited by 470
  12. 2024YOLOv11: An Overview of the Key Architectural Enhancementscited by 425
38 more
  1. 2017MoDL: Model Based Deep Learning Architecture for Inverse Problemscited by 387
  2. 2017Learning a Variational Network for Reconstruction of Accelerated MRI Datacited by 342
  3. 2021Score-based diffusion models for accelerated MRIcited by 311
  4. 2021Robust Compressed Sensing MRI with Deep Generative Priorscited by 286
  5. 2017Advances in Variational Inferencecited by 236
  6. 2022Diffusion probabilistic modeling of protein backbones in 3D for the motif-scaffolding problemcited by 236
  7. 2017A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstructioncited by 232
  8. 2017Image reconstruction by domain transform manifold learningcited by 232
  9. 2023Practical and Asymptotically Exact Conditional Sampling in Diffusion Modelscited by 232
  10. 2017Deep learning for undersampled MRI reconstructioncited by 91
  11. 2020Structured Logconcave Sampling with a Restricted Gaussian Oraclecited by 86
  12. 2017Compressed Sensing MRI Reconstruction using a Generative Adversarial Network with a Cyclic Losscited by 82
  13. 2022Improved analysis for a proximal algorithm for samplingcited by 73
  14. 2018An Online Plug-and-Play Algorithm for Regularized Image Reconstructioncited by 70
  15. 2019A Theoretical and Empirical Comparison of Gradient Approximations in Derivative-Free Optimizationcited by 68
  16. 2019RARE: Image Reconstruction using Deep Priors Learned without Ground Truthcited by 64
  17. 2020Deep Probabilistic Imaging: Uncertainty Quantification and Multi-modal Solution Characterization for Computational Imagingcited by 57
  18. 2024Symbolic Music Generation with Non-Differentiable Rule Guided Diffusioncited by 54
  19. 2023Provable Probabilistic Imaging using Score-Based Generative Priorscited by 51
  20. 2021Recovery of Continuous 3D Refractive Index Maps from Discrete Intensity-Only Measurements using Neural Fieldscited by 48
  21. 2018Split-and-augmented Gibbs sampler - Application to large-scale inference problemscited by 47
  22. 2022Bayesian MRI Reconstruction with Joint Uncertainty Estimation using Diffusion Modelscited by 47
  23. 2021OpenFWI: Large-Scale Multi-Structural Benchmark Datasets for Seismic Full Waveform Inversioncited by 44
  24. 2017MR image reconstruction using deep density priorscited by 37
  25. 2018Ensemble Kalman Inversion: A Derivative-Free Technique For Machine Learning Taskscited by 37
  26. 2018DeepNIS: Deep Neural Network for Nonlinear Electromagnetic Inverse Scatteringcited by 31
  27. 2019MRI Reconstruction Using Deep Bayesian Estimationcited by 29
  28. 2021fastMRI+: Clinical Pathology Annotations for Knee and Brain Fully Sampled Multi-Coil MRI Datacited by 29
  29. 2023A Latent Diffusion Model for Protein Structure Generationcited by 28
  30. 2018Deep speckle correlation: a deep learning approach towards scalable imaging through scattering mediacited by 23
  31. 2021SGD-Net: Efficient Model-Based Deep Learning with Theoretical Guaranteescited by 18
  32. 2019SIMBA: Scalable Inversion in Optical Tomography using Deep Denoising Priorscited by 16
  33. 2019Diffraction tomography with a deep image priorcited by 15
  34. 2015Fast Multi-class Dictionaries Learning with Geometrical Directions in MRI Reconstructioncited by 10
  35. 2018Efficient and accurate inversion of multiple scattering with deep learningcited by 10
  36. 2024Event-horizon-scale Imaging of M87* under Different Assumptions via Deep Generative Image Priorscited by 7
  37. 2013Bayesian Nonparametric Dictionary Learning for Compressed Sensing MRIcited by 5
  38. 2017SEAGLE: Sparsity-Driven Image Reconstruction under Multiple Scatteringcited by 5

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 24; 2026: 44.

68 papers.

Sort:

By area:

  1. 2025Training a Scientific Reasoning Model for Chemistrycited by 56
  2. 2025DriftLite: Lightweight Drift Control for Inference-Time Scaling of Diffusion Modelscited by 23
  3. 2025Solving Inverse Problems via Diffusion-Based Priors: An Approximation-Free Ensemble Sampling Approachcited by 18
  4. 2026RealPDEBench: A Benchmark for Complex Physical Systems with Real-World Datacited by 16
  5. 2025Physics-Informed Distillation of Diffusion Models for PDE-Constrained Generationcited by 11
  6. 2025Steering Generative Models with Experimental Data for Protein Fitness Optimizationcited by 7
  7. 2026CCTU: A Benchmark for Tool Use under Complex Constraintscited by 7
  8. 2025Whitened Score Diffusion: A Structured Prior for Imaging Inverse Problemscited by 6
  9. 2025Good Things Come in Pairs: Paired Autoencoders for Inverse Problemscited by 5
  10. 2025FD-Bench: A Modular and Fair Benchmark for Data-driven Fluid Simulationcited by 5
  11. 2025Blade: A Derivative-free Bayesian Inversion Method using Diffusion Priorscited by 5
  12. 2025DAISI: Data Assimilation with Inverse Sampling using Stochastic Interpolantscited by 5
38 more
  1. 2026Calibrated Test-Time Guidance for Bayesian Inferencecited by 5
  2. 2025Continuous Representation Methods, Theories, and Applications: An Overview and Perspectivescited by 4
  3. 2025Multiphysics Bench: Benchmarking and Investigating Scientific Machine Learning for Multiphysics PDEscited by 4
  4. 2025Enforcing governing equation constraints in neural PDE solvers via training-free projectionscited by 4
  5. 2026Weak Diffusion Priors Can Still Achieve Strong Inverse-Problem Performancecited by 4
  6. 2025STeP: A Framework for Solving Scientific Video Inverse Problems with Spatiotemporal Diffusion Priorscited by 3
  7. 2025Physics-Aware Neural Operators for Direct Inversion in 3D Photoacoustic Tomographycited by 3
  8. 2025Noise is All You Need: Solving Linear Inverse Problems by Noise Combination Sampling with Diffusion Modelscited by 3
  9. 2026Sample-efficient evidence estimation of score based priors for model selectioncited by 3
  10. 2026On the Robustness of Langevin Dynamics to Score Function Errorcited by 3
  11. 2026Adaptive Diffusion Posterior Sampling for Data and Model Fusion of Complex Nonlinear Dynamical Systemscited by 3
  12. 2026SimulCost: A Cost-Aware Benchmark and Toolkit for Automating Physics Simulations with LLMscited by 3
  13. 2025Blind Strong Gravitational Lensing Inversion: Joint Inference of Source and Lens Mass with Score-Based Modelscited by 2
  14. 2025Latent Refinement via Flow Matching for Training-free Linear Inverse Problem Solvingcited by 2
  15. 2026Ultra Fast PDE Solving via Physics Guided Few-step Diffusioncited by 2
  16. 2026Noise-Adaptive Diffusion Sampling for Inverse Problems Without Task-Specific Tuningcited by 2
  17. 2026A Stability Benchmark of Generative Regularizers for Inverse Problemscited by 2
  18. 2026PDEInvBench: A Comprehensive Dataset and Design Space Exploration of Neural Networks for PDE Inverse Problemscited by 2
  19. 2025Diffusion Probabilistic Generative Models for Accelerated, in-NICU Permanent Magnet Neonatal MRIcited by 1
  20. 2025Measurement-Aligned Sampling for Inverse Problemcited by 1
  21. 2025Contrastive Diffusion Guidance for Spatial Inverse Problemscited by 1
  22. 2026Outlier-robust Diffusion Posterior Sampling for Bayesian Inverse Problemscited by 1
  23. 2026Constrained Particle Seeking: Solving Diffusion Inverse Problems with Just Forward Passescited by 1
  24. 2026Mapping Dark-Matter Clusters via Physics-Guided Diffusion Modelscited by 1
  25. 2026Unveiling the Mechanism of Continuous Representation Full-Waveform Inversion: A Wave Based Neural Tangent Kernel Frameworkcited by 1
  26. 2026Optimizing Diffusion Priors in Image Reconstruction from a Single Observationcited by 1
  27. 2026Pointwise Metrics Mislead: An Evaluation Protocol for Multimodal Inverse Problemscited by 1
  28. 2026Zeroth-Order Non-Log-Concave Sampling with Variance Reduction and Applications to Inverse Problemscited by 1
  29. 2026ShuffleFlow: Scalable Posterior Inference for Bayesian Inverse Imagingcited by 1
  30. 2025Plug-and-play Diffusion Models for Image Compressive Sensing with Data Consistency Projectioncited by 0
  31. 2025Deep generative priors for 3D brain analysiscited by 0
  32. 2025Uncertainty Quantification in HSI Reconstruction using Physics-Aware Diffusion Priors and Optics-Encoded Measurementscited by 0
  33. 2026Latent Space Inference via Paired Autoencoderscited by 0
  34. 2026GraIP: A Benchmarking Framework For Neural Graph Inverse Problemscited by 0
  35. 2026Beyond Accuracy: Evaluating Posterior Fidelity of Diffusion Inverse Solverscited by 0
  36. 2026Escaping Spectral Bias without Backpropagation: Fast Implicit Neural Representations with Extreme Learning Machinescited by 0
  37. 2026Plug-and-Play Diffusion Meets ADMM: Dual-Variable Coupling for Robust Medical Image Reconstructioncited by 0
  38. 2026Solving a Nonlinear Blind Inverse Problem for Tagged MRI with Physics and Deep Generative Priorscited by 0

50 most cited of 68 All 68 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Diffusion models for inverse problems
  2. 2024Enhancing and Accelerating Diffusion-Based Inverse Problem Solving through Measurements Optimization
  3. 2025Benchmarking Diffusion Annealing-Based Bayesian Inverse Problem Solvers
  4. 2025Unifying and extending Diffusion Models through PDEs for solving Inverse Problems
  5. 2025PnP-CM: Consistency Models as Plug-and-Play Priors for Inverse Problems
  6. 2025ReGuidance: A Simple Diffusion Wrapper for Boosting Sample Quality on Hard Inverse Problems
  7. 2025Solving Diffusion Inverse Problems with Restart Posterior Sampling
  8. 2023Direct Diffusion Bridge using Data Consistency for Inverse Problems