Solving Linear Inverse Problems using Higher-Order Annealed Langevin Diffusion

N Zilberstein, A Sabharwal… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
We propose a solution for linear inverse problems based on higher-order Langevin
diffusion. More precisely, we propose pre-conditioned second-order and third-order …

NF-ULA: Langevin Monte Carlo with normalizing flow prior for imaging inverse problems

Z Cai, J Tang, S Mukherjee, J Li, CB Schönlieb… - arXiv preprint arXiv …, 2023 - arxiv.org
Bayesian methods for solving inverse problems are a powerful alternative to classical
methods since the Bayesian approach gives a probabilistic description of the problems and …

Proximal Langevin Sampling With Inexact Proximal Mapping

MJ Ehrhardt, L Kuger, CB Schönlieb - arXiv preprint arXiv:2306.17737, 2023 - arxiv.org
In order to solve tasks like uncertainty quantification or hypothesis tests in Bayesian imaging
inverse problems, we often have to draw samples from the arising posterior distribution. For …

Posterior-Variance–Based Error Quantification for Inverse Problems in Imaging

D Narnhofer, A Habring, M Holler, T Pock - SIAM Journal on Imaging Sciences, 2024 - SIAM
In this work, a method for obtaining pixelwise error bounds in Bayesian regularization of
inverse imaging problems is introduced. The proposed method employs estimates of the …

Solving inverse problems with latent diffusion models via hard data consistency

B Song, SM Kwon, Z Zhang, X Hu, Q Qu… - arXiv preprint arXiv …, 2023 - arxiv.org
Diffusion models have recently emerged as powerful generative priors for solving inverse
problems. However, training diffusion models in the pixel space are both data intensive and …

Distributed iterative thresholding for ℓ0/ℓ1-regularized linear inverse problems

C Ravazzi, SM Fosson, E Magli - IEEE Transactions on …, 2015 - ieeexplore.ieee.org
The ℓ 0/ℓ 1-regularized least-squares approach is used to deal with linear inverse problems
under sparsity constraints, which arise in mathematical and engineering fields. In particular …

A variational perspective on solving inverse problems with diffusion models

M Mardani, J Song, J Kautz, A Vahdat - arXiv preprint arXiv:2305.04391, 2023 - arxiv.org
Diffusion models have emerged as a key pillar of foundation models in visual domains. One
of their critical applications is to universally solve different downstream inverse tasks via a …

NF-ULA: Normalizing Flow-Based Unadjusted Langevin Algorithm for Imaging Inverse Problems

Z Cai, J Tang, S Mukherjee, J Li, CB Schönlieb… - SIAM Journal on Imaging …, 2024 - SIAM
Bayesian methods for solving inverse problems are a powerful alternative to classical
methods since the Bayesian approach offers the ability to quantify the uncertainty in the …

Fast diffusion sampler for inverse problems by geometric decomposition

H Chung, S Lee, JC Ye - arXiv preprint arXiv:2303.05754, 2023 - arxiv.org
Krylov subspace, which is generated by multiplying a given vector by the matrix of a linear
transformation and its successive powers, has been extensively studied in classical …

Tweedie moment projected diffusions for inverse problems

B Boys, M Girolami, J Pidstrigach, S Reich… - arXiv preprint arXiv …, 2023 - arxiv.org
Diffusion generative models unlock new possibilities for inverse problems as they allow for
the incorporation of strong empirical priors into the process of scientific inference. Recently …