Diffusion Posterior Sampling for General Noisy Inverse Problems

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chung, Hyungjin, Kim, Jeongsol, Mccann, Michael T., Klasky, Marc L., Ye, Jong Chul
Format: Preprint
Veröffentlicht: 2022
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912624045719552
author Chung, Hyungjin
Kim, Jeongsol
Mccann, Michael T.
Klasky, Marc L.
Ye, Jong Chul
author_facet Chung, Hyungjin
Kim, Jeongsol
Mccann, Michael T.
Klasky, Marc L.
Ye, Jong Chul
contents Diffusion models have been recently studied as powerful generative inverse problem solvers, owing to their high quality reconstructions and the ease of combining existing iterative solvers. However, most works focus on solving simple linear inverse problems in noiseless settings, which significantly under-represents the complexity of real-world problems. In this work, we extend diffusion solvers to efficiently handle general noisy (non)linear inverse problems via approximation of the posterior sampling. Interestingly, the resulting posterior sampling scheme is a blended version of diffusion sampling with the manifold constrained gradient without a strict measurement consistency projection step, yielding a more desirable generative path in noisy settings compared to the previous studies. Our method demonstrates that diffusion models can incorporate various measurement noise statistics such as Gaussian and Poisson, and also efficiently handle noisy nonlinear inverse problems such as Fourier phase retrieval and non-uniform deblurring. Code available at https://github.com/DPS2022/diffusion-posterior-sampling
format Preprint
id arxiv_https___arxiv_org_abs_2209_14687
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Diffusion Posterior Sampling for General Noisy Inverse Problems
Chung, Hyungjin
Kim, Jeongsol
Mccann, Michael T.
Klasky, Marc L.
Ye, Jong Chul
Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Diffusion models have been recently studied as powerful generative inverse problem solvers, owing to their high quality reconstructions and the ease of combining existing iterative solvers. However, most works focus on solving simple linear inverse problems in noiseless settings, which significantly under-represents the complexity of real-world problems. In this work, we extend diffusion solvers to efficiently handle general noisy (non)linear inverse problems via approximation of the posterior sampling. Interestingly, the resulting posterior sampling scheme is a blended version of diffusion sampling with the manifold constrained gradient without a strict measurement consistency projection step, yielding a more desirable generative path in noisy settings compared to the previous studies. Our method demonstrates that diffusion models can incorporate various measurement noise statistics such as Gaussian and Poisson, and also efficiently handle noisy nonlinear inverse problems such as Fourier phase retrieval and non-uniform deblurring. Code available at https://github.com/DPS2022/diffusion-posterior-sampling
title Diffusion Posterior Sampling for General Noisy Inverse Problems
topic Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2209.14687