Fast Diffusion EM: a diffusion model for blind inverse problems with application to deconvolution

by   Charles Laroche, et al.
Université Paris Descartes

Using diffusion models to solve inverse problems is a growing field of research. Current methods assume the degradation to be known and provide impressive results in terms of restoration quality and diversity. In this work, we leverage the efficiency of those models to jointly estimate the restored image and unknown parameters of the degradation model. In particular, we designed an algorithm based on the well-known Expectation-Minimization (EM) estimation method and diffusion models. Our method alternates between approximating the expected log-likelihood of the inverse problem using samples drawn from a diffusion model and a maximization step to estimate unknown model parameters. For the maximization step, we also introduce a novel blur kernel regularization based on a Plug & Play denoiser. Diffusion models are long to run, thus we provide a fast version of our algorithm. Extensive experiments on blind image deblurring demonstrate the effectiveness of our method when compared to other state-of-the-art approaches.


page 2

page 7

page 8


Parallel Diffusion Models of Operator and Image for Blind Inverse Problems

Diffusion model-based inverse problem solvers have demonstrated state-of...

INDigo: An INN-Guided Probabilistic Diffusion Algorithm for Inverse Problems

Recently it has been shown that using diffusion models for inverse probl...

Learning Generic Diffusion Processes for Image Restoration

Image restoration problems are typical ill-posed problems where the regu...

End-To-End Latent Variational Diffusion Models for Inverse Problems in High Energy Physics

High-energy collisions at the Large Hadron Collider (LHC) provide valuab...

DiracDiffusion: Denoising and Incremental Reconstruction with Assured Data-Consistency

Diffusion models have established new state of the art in a multitude of...

On inverse doping profile problems for the stationary voltage-current map

We consider the problem of identifying possibly discontinuous doping pro...

Please sign up or login with your details

Forgot password? Click here to reset