# Inverse problems and image restoration Area: [Diffusion models](https://mlsanity.com/diffusion/index.md). HTML: https://mlsanity.com/diffusion/inverse-problems-and-image-restoration/ ## Key facts - Inverse problems and image restoration: 1,043 papers on arXiv since 2021 (data through 14 Oct 2026). - 330 of its 1,043 mapped papers (32%) cite “Denoising Diffusion Restoration Models” (2022, arXiv 2201.11793). - 310 of its 1,043 mapped papers (30%) cite “Diffusion Posterior Sampling for General Noisy Inverse Problems” (2022, arXiv 2209.14687). - 38 new papers 17 Sep–14 Oct. ## Most cited here - [Denoising Diffusion Restoration Models](https://mlsanity.com/paper/2201.11793/) (2022), cited by 330 papers here - [Diffusion Posterior Sampling for General Noisy Inverse Problems](https://mlsanity.com/paper/2209.14687/) (2022), cited by 310 papers here - [Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model](https://mlsanity.com/paper/2212.00490/) (2022), cited by 227 papers here - [Exploiting Diffusion Prior for Real-World Image Super-Resolution](https://mlsanity.com/paper/2305.07015/) (2023), cited by 221 papers here - [ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting](https://mlsanity.com/paper/2307.12348/) (2023), cited by 155 papers here - [SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution](https://mlsanity.com/paper/2311.16518/) (2023), cited by 149 papers here - [Improving Diffusion Models for Inverse Problems using Manifold Constraints](https://mlsanity.com/paper/2206.00941/) (2022), cited by 140 papers here - [Denoising Diffusion Models for Plug-and-Play Image Restoration](https://mlsanity.com/paper/2305.08995/) (2023), cited by 139 papers here - [Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylization](https://mlsanity.com/paper/2308.14469/) (2023), cited by 137 papers here - [DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior](https://mlsanity.com/paper/2308.15070/) (2023), cited by 115 papers here ## New (17 Sep–14 Oct) - [Structure-aware Bayesian full waveform inversion via diffusion-regularized Stein variational gradient descent](https://mlsanity.com/paper/2610.19187/) (2026-10-13) - [AReA: Adaptive Receptive-Field Attention for Efficient High-Resolution Diffusion Transformers](https://mlsanity.com/paper/2610.17227/) (2026-10-12) - [OmniRSI: Taming Latent Diffusion for Unified Multimodal Remote Sensing Image Generation](https://mlsanity.com/paper/2610.15414/) (2026-10-11) - [MOSAIC: Multi-Scale Object-Centric Slot Adaptation with Image-Guided Prototype Conditioning for Remote Sensing Image Super-Resolution](https://mlsanity.com/paper/2610.13547/) (2026-10-09) - [Kinetic Langevin Meets Split Gibbs: Accelerated Posterior Sampling for Imaging Inverse Problems with Diffusion Priors](https://mlsanity.com/paper/2610.10187/) (2026-10-07) - [Iris-3B: Going Beyond the Latent with Pixel-Space Diffusion Training, Conversion and Fine-Tuning](https://mlsanity.com/paper/2610.09450/) (2026-10-07) - [Noise, Denoise, Correct: MCMC Posterior Sampling with Diffusion Priors in Three Steps](https://mlsanity.com/paper/2610.09407/) (2026-10-07) - [DISRQAD: Diffusion Image Super-Resolution Quality Assessment Dataset and Benchmark](https://mlsanity.com/paper/2610.09077/) (2026-10-06) - [LiDAR Resolution Recovery via Foundation-Model-Guided Diffusion](https://mlsanity.com/paper/2610.08620/) (2026-10-06) - [Energy-Conditioned Noise Schedule and Whitening for Spectral Diffusion](https://mlsanity.com/paper/2610.07206/) (2026-10-05) - [Frequency-Decoupled Diffusion Guidance for Non-Blind Image Deblurring](https://mlsanity.com/paper/2610.06221/) (2026-10-05) - [Diffusion Meets Unrolling: Compressive SAR Image Reconstruction with Interleaved Learned Corrections](https://mlsanity.com/paper/2610.06107/) (2026-10-05) - [Robust Ensemble Guidance for Scientific Inverse Problems](https://mlsanity.com/paper/2610.05371/) (2026-10-04) - [DriftSR: One-Step Real-World Image Super-Resolution via Distribution Drifting](https://mlsanity.com/paper/2610.04819/) (2026-10-03) - [Measuring Effective Data Resolution in Guided Diffusion Posteriors](https://mlsanity.com/paper/2610.04422/) (2026-10-03) - [Dynamic Time Step Prediction in Inverse Heat Dissipation for Blur-Like Image Restoration Tasks](https://mlsanity.com/paper/2610.03942/) (2026-10-02) - [Consecutive Posterior Fusion for Diffusive Recovery of Unobservable Image Structures](https://mlsanity.com/paper/2610.03261/) (2026-10-02) - [Domain-adaptive Zero-Shot Image Enhancement via Locality-Constrained Diffusion Guidance](https://mlsanity.com/paper/2609.35289/) (2026-09-28) - [GPARA: Graph-Posterior-Aligned Refinement and Active Acquisition for Grounding Diffusion Priors](https://mlsanity.com/paper/2609.34172/) (2026-09-28) - [SNaP: One-Step Posterior Sampling for Noisy Inverse Problems](https://mlsanity.com/paper/2609.34071/) (2026-09-28) - [CLIMB-flow: Coupled Linear Inverse posterior sampling via Multiscale-Based flow](https://mlsanity.com/paper/2609.33834/) (2026-09-27) - [Fill2SR: Repurposing Inpainting Diffusion Transformers for Real-World Super-Resolution](https://mlsanity.com/paper/2609.33582/) (2026-09-27) - [In-Token Learning for High-Fidelity Image Restoration via Diffusion Transformers](https://mlsanity.com/paper/2609.33523/) (2026-09-27) - [Structured Residual Connectivity Matters for Diffusion Transformers](https://mlsanity.com/paper/2609.33203/) (2026-09-27) - [Perturb-and-Solve: Efficient Learned-Operator Conditioning for Latent Diffusion Inverse Problems](https://mlsanity.com/paper/2609.33171/) (2026-09-27) - [Residual Diffusion Implicit Models](https://mlsanity.com/paper/2609.33020/) (2026-09-26) - [ANaLOG: Anisotropic Native-Latent Operator Guidance for Solving Inverse Problems](https://mlsanity.com/paper/2609.31933/) (2026-09-25) - [ContraFM-S2O: Flow Matching-Based One-step SAR-to-Optical Image Translation Model with Contrastive Learning](https://mlsanity.com/paper/2609.31378/) (2026-09-25) - [PhoenixSR: Generative Heterogeneous Distillation Unleashes Efficient Models for Real-World Super-Resolution](https://mlsanity.com/paper/2609.30988/) (2026-09-25) - [Learning to Replace MCMC in Split-Gibbs Diffusion Posterior Sampling via Deep Unfolding](https://mlsanity.com/paper/2609.30539/) (2026-09-24)