Denoising Diffusion Restoration Models

by   Bahjat Kawar, et al.

Many interesting tasks in image restoration can be cast as linear inverse problems. A recent family of approaches for solving these problems uses stochastic algorithms that sample from the posterior distribution of natural images given the measurements. However, efficient solutions often require problem-specific supervised training to model the posterior, whereas unsupervised methods that are not problem-specific typically rely on inefficient iterative methods. This work addresses these issues by introducing Denoising Diffusion Restoration Models (DDRM), an efficient, unsupervised posterior sampling method. Motivated by variational inference, DDRM takes advantage of a pre-trained denoising diffusion generative model for solving any linear inverse problem. We demonstrate DDRM's versatility on several image datasets for super-resolution, deblurring, inpainting, and colorization under various amounts of measurement noise. DDRM outperforms the current leading unsupervised methods on the diverse ImageNet dataset in reconstruction quality, perceptual quality, and runtime, being 5x faster than the nearest competitor. DDRM also generalizes well for natural images out of the distribution of the observed ImageNet training set.


page 8

page 20

page 22

page 23

page 24

page 25

page 26

page 27


Generative Diffusion Prior for Unified Image Restoration and Enhancement

Existing image restoration methods mostly leverage the posterior distrib...

A Variational Perspective on Solving Inverse Problems with Diffusion Models

Diffusion models have emerged as a key pillar of foundation models in vi...

Solving Linear Inverse Problems Provably via Posterior Sampling with Latent Diffusion Models

We present the first framework to solve linear inverse problems leveragi...

DDS2M: Self-Supervised Denoising Diffusion Spatio-Spectral Model for Hyperspectral Image Restoration

Diffusion models have recently received a surge of interest due to their...

Bi-Noising Diffusion: Towards Conditional Diffusion Models with Generative Restoration Priors

Conditional diffusion probabilistic models can model the distribution of...

Ultrasound Image Reconstruction with Denoising Diffusion Restoration Models

Ultrasound image reconstruction can be approximately cast as a linear in...

SNIPS: Solving Noisy Inverse Problems Stochastically

In this work we introduce a novel stochastic algorithm dubbed SNIPS, whi...

Please sign up or login with your details

Forgot password? Click here to reset