# Blind Image Restoration via Fast Diffusion Inversion

arXiv: https://arxiv.org/abs/2405.19572 · HTML: https://mlsanity.com/paper/2405.19572/

## Key facts

- Cited by 30 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 24 of its 29 references that are in the map.
- First posted on arXiv 29 May 2024.

## Placed in

- Diffusion models / [Inverse problems and image restoration](https://mlsanity.com/diffusion/inverse-problems-and-image-restoration/)

## Builds on (most cited first, 24 of 24)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [RePaint: Inpainting using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2201.09865/) (2022)
- [Diffusion Posterior Sampling for General Noisy Inverse Problems](https://mlsanity.com/paper/2209.14687/) (2022)
- [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Denoising Diffusion Restoration Models](https://mlsanity.com/paper/2201.11793/) (2022)
- [Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model](https://mlsanity.com/paper/2212.00490/) (2022)
- [Improving Diffusion Models for Inverse Problems using Manifold Constraints](https://mlsanity.com/paper/2206.00941/) (2022)
- [Plug-and-Play Image Restoration with Deep Denoiser Prior](https://mlsanity.com/paper/2008.13751/) (2020)
- [PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models](https://mlsanity.com/paper/2003.03808/) (2020)
- [Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation](https://mlsanity.com/paper/2003.13659/) (2020)
- [Generative Diffusion Prior for Unified Image Restoration and Enhancement](https://mlsanity.com/paper/2304.01247/) (2023)
- [GAN Prior Embedded Network for Blind Face Restoration in the Wild](https://mlsanity.com/paper/2105.06070/) (2021)
- [StyleSwin: Transformer-based GAN for High-resolution Image Generation](https://mlsanity.com/paper/2112.10762/) (2021)
- [Neural Blind Deconvolution Using Deep Priors](https://mlsanity.com/paper/1908.02197/) (2019)
- [Parallel Diffusion Models of Operator and Image for Blind Inverse Problems](https://mlsanity.com/paper/2211.10656/) (2022)
- [Intermediate Layer Optimization for Inverse Problems using Deep Generative Models](https://mlsanity.com/paper/2102.07364/) (2021)
- [GibbsDDRM: A Partially Collapsed Gibbs Sampler for Solving Blind Inverse Problems with Denoising Diffusion Restoration](https://mlsanity.com/paper/2301.12686/) (2023)
- [Fast Diffusion EM: a diffusion model for blind inverse problems with application to deconvolution](https://mlsanity.com/paper/2309.00287/) (2023)
- [High-Fidelity Image Inpainting with GAN Inversion](https://mlsanity.com/paper/2208.11850/) (2022)
- [Robust Unsupervised StyleGAN Image Restoration](https://mlsanity.com/paper/2302.06733/) (2023)

## Built on by (most cited first, 30 of 30)

- [Arbitrary-steps Image Super-resolution via Diffusion Inversion](https://mlsanity.com/paper/2412.09013/) (2024)
- [Reconciling Stochastic and Deterministic Strategies for Zero-shot Image Restoration using Diffusion Model in Dual](https://mlsanity.com/paper/2503.01288/) (2025)
- [Improving Robotic Generalist Policies via Flow Reversal Steering](https://mlsanity.com/paper/2606.13675/) (2026)
- [Oscillation Inversion: Understand the structure of Large Flow Model through the Lens of Inversion Method](https://mlsanity.com/paper/2411.11135/) (2024)
- [Weak Diffusion Priors Can Still Achieve Strong Inverse-Problem Performance](https://mlsanity.com/paper/2601.22443/) (2026)
- [Uni-Flow: a unified autoregressive-diffusion model for complex multiscale flows](https://mlsanity.com/paper/2602.15592/) (2026)
- [Polarization Uncertainty-Guided Diffusion Model for Color Polarization Image Demosaicking](https://mlsanity.com/paper/2602.23847/) (2026)
- [One-Step Residual Shifting Diffusion for Image Super-Resolution via Distillation](https://mlsanity.com/paper/2503.13358/) (2025)
- [Diffusion Image Prior](https://mlsanity.com/paper/2503.21410/) (2025)
- [Adaptive Weighted h-Transform Sampling for Coarse-Guided Visual Generation](https://mlsanity.com/paper/2603.12057/) (2026)
- [MENO: MeanFlow-Enhanced Neural Operators for Dynamical Systems](https://mlsanity.com/paper/2604.06881/) (2026)
- [Blind Strong Gravitational Lensing Inversion: Joint Inference of Source and Lens Mass with Score-Based Models](https://mlsanity.com/paper/2511.04792/) (2025)
- [Trajectory Stitching for Solving Inverse Problems with Flow-Based Models](https://mlsanity.com/paper/2602.08538/) (2026)
- [A Stability Benchmark of Generative Regularizers for Inverse Problems](https://mlsanity.com/paper/2605.10076/) (2026)
- [Couple to Control: Joint Initial Noise Design in Diffusion Models](https://mlsanity.com/paper/2605.11311/) (2026)
- [Blind Inverse Problem Solving Made Easy by Text-to-Image Latent Diffusion](https://mlsanity.com/paper/2412.00557/) (2024)
- [Dream-IF: Dynamic Relative EnhAnceMent for Image Fusion](https://mlsanity.com/paper/2503.10109/) (2025)
- [Invert2Restore: Zero-Shot Degradation-Blind Image Restoration](https://mlsanity.com/paper/2503.21486/) (2025)
- [Zero-shot CT Super-Resolution using Diffusion-based 2D Projection Priors and Signed 3D Gaussians](https://mlsanity.com/paper/2508.15151/) (2025)
- [On the Sample Complexity of Learning for Blind Inverse Problems](https://mlsanity.com/paper/2512.23405/) (2025)
- [Beyond Prompts: Unconditional 3D Inversion for Out-of-Distribution Shapes](https://mlsanity.com/paper/2604.14914/) (2026)
- [PolarVSR: A Unified Framework and Benchmark for Continuous Space-Time Polarization Video Reconstruction](https://mlsanity.com/paper/2605.10275/) (2026)
- [LatentINDIGO: An INN-Guided Latent Diffusion Algorithm for Image Restoration](https://mlsanity.com/paper/2505.12935/) (2025)
- [Generative Latent Kernel Modeling for Blind Motion Deblurring](https://mlsanity.com/paper/2507.09285/) (2025)
- [Extreme Blind Image Restoration via Prompt-Conditioned Information Bottleneck](https://mlsanity.com/paper/2510.00728/) (2025)
- [A Comparative Study of MAP and LMMSE Estimators for Blind Inverse Problems](https://mlsanity.com/paper/2602.11814/) (2026)
- [Beyond Fixed Inference: Quantitative Flow Matching for Adaptive Image Denoising](https://mlsanity.com/paper/2604.02392/) (2026)
- [P-Flow: Proxy-gradient Flows for Linear Inverse Problems](https://mlsanity.com/paper/2605.08328/) (2026)
- [MDTD-ArtIR: Benchmarking Image Editing and Restoration Models for Art Image Restoration under Texture-Overlay Degradations](https://mlsanity.com/paper/2608.00736/) (2026)
- [Dynamic Time Step Prediction in Inverse Heat Dissipation for Blur-Like Image Restoration Tasks](https://mlsanity.com/paper/2610.03942/) (2026)

## Abstract (arXiv)

Image Restoration (IR) methods based on a pre-trained diffusion model have demonstrated state-of-the-art performance. However, they have two fundamental limitations: 1) they often assume that the degradation operator is completely known and 2) they alter the diffusion sampling process, which may result in restored images that do not lie onto the data manifold. To address these issues, we propose Blind Image Restoration via fast Diffusion inversion (BIRD) a blind IR method that jointly optimizes for the degradation model parameters and the restored image. To ensure that the restored images lie onto the data manifold, we propose a novel sampling technique on a pre-trained diffusion model. A key idea in our method is not to modify the reverse sampling, i.e, not to alter all the intermediate latents, once an initial noise is sampled. This is ultimately equivalent to casting the IR task as an optimization problem in the space of the input noise. Moreover, to mitigate the computational cost associated with inverting a fully unrolled diffusion model, we leverage the inherent capability of these models to skip ahead in the forward diffusion process using large time steps. We experimentally validate BIRD on several image restoration tasks and show that it achieves state of the art performance on all of them. Our code is available at https://github.com/hamadichihaoui/BIRD.