Think Twice Before You Act: Improving Inverse Problem Solving With MCMC
- URL: http://arxiv.org/abs/2409.08551v1
- Date: Fri, 13 Sep 2024 06:10:54 GMT
- Title: Think Twice Before You Act: Improving Inverse Problem Solving With MCMC
- Authors: Yaxuan Zhu, Zehao Dou, Haoxin Zheng, Yasi Zhang, Ying Nian Wu, Ruiqi Gao,
- Abstract summary: We propose textbfDiffusion textbfPosterior textbfMCMC (textbfDPMC) to solve inverse problems with pretrained diffusion models.
Our algorithm outperforms DPS with less number of evaluations across nearly all tasks, and is competitive among existing approaches.
- Score: 40.5682961122897
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Recent studies demonstrate that diffusion models can serve as a strong prior for solving inverse problems. A prominent example is Diffusion Posterior Sampling (DPS), which approximates the posterior distribution of data given the measure using Tweedie's formula. Despite the merits of being versatile in solving various inverse problems without re-training, the performance of DPS is hindered by the fact that this posterior approximation can be inaccurate especially for high noise levels. Therefore, we propose \textbf{D}iffusion \textbf{P}osterior \textbf{MC}MC (\textbf{DPMC}), a novel inference algorithm based on Annealed MCMC to solve inverse problems with pretrained diffusion models. We define a series of intermediate distributions inspired by the approximated conditional distributions used by DPS. Through annealed MCMC sampling, we encourage the samples to follow each intermediate distribution more closely before moving to the next distribution at a lower noise level, and therefore reduce the accumulated error along the path. We test our algorithm in various inverse problems, including super resolution, Gaussian deblurring, motion deblurring, inpainting, and phase retrieval. Our algorithm outperforms DPS with less number of evaluations across nearly all tasks, and is competitive among existing approaches.
Related papers
- A Mixture-Based Framework for Guiding Diffusion Models [19.83064246586143]
Denoising diffusion models have driven significant progress in the field of Bayesian inverse problems.
Recent approaches use pre-trained diffusion models as priors to solve a wide range of such problems.
This work proposes a novel mixture approximation of these intermediate distributions.
arXiv Detail & Related papers (2025-02-05T16:26:06Z) - Geophysical inverse problems with measurement-guided diffusion models [0.4532517021515834]
I consider two sampling algorithms recently proposed under the name of Diffusion Posterior Sampling (DPS) and Pseudo-inverse Guided Diffusion Model (PGDM)
In DPS, the guidance term is obtained by applying the adjoint of the modeling operator to the residual obtained from a one-step denoising estimate of the solution.
On the other hand, PGDM utilizes a pseudo-inverse operator that originates from the fact that the one-step denoised solution is not assumed to be deterministic.
arXiv Detail & Related papers (2025-01-08T23:33:50Z) - Enhancing Diffusion Models for Inverse Problems with Covariance-Aware Posterior Sampling [3.866047645663101]
In computer vision, for example, tasks such as inpainting, deblurring, and super resolution can be effectively modeled as inverse problems.
DDPMs are shown to provide a promising solution to noisy linear inverse problems without the need for additional task specific training.
arXiv Detail & Related papers (2024-12-28T06:17:44Z) - Diffusion Prior-Based Amortized Variational Inference for Noisy Inverse Problems [12.482127049881026]
We propose a novel approach to solve inverse problems with a diffusion prior from an amortized variational inference perspective.
Our amortized inference learns a function that directly maps measurements to the implicit posterior distributions of corresponding clean data, enabling a single-step posterior sampling even for unseen measurements.
arXiv Detail & Related papers (2024-07-23T02:14:18Z) - Divide-and-Conquer Posterior Sampling for Denoising Diffusion Priors [21.0128625037708]
We present an innovative framework, divide-and-conquer posterior sampling.
It reduces the approximation error associated with current techniques without the need for retraining.
We demonstrate the versatility and effectiveness of our approach for a wide range of Bayesian inverse problems.
arXiv Detail & Related papers (2024-03-18T01:47:24Z) - Ambient Diffusion Posterior Sampling: Solving Inverse Problems with
Diffusion Models trained on Corrupted Data [56.81246107125692]
Ambient Diffusion Posterior Sampling (A-DPS) is a generative model pre-trained on one type of corruption.
We show that A-DPS can sometimes outperform models trained on clean data for several image restoration tasks in both speed and performance.
We extend the Ambient Diffusion framework to train MRI models with access only to Fourier subsampled multi-coil MRI measurements.
arXiv Detail & Related papers (2024-03-13T17:28:20Z) - A Variational Perspective on Solving Inverse Problems with Diffusion
Models [101.831766524264]
Inverse tasks can be formulated as inferring a posterior distribution over data.
This is however challenging in diffusion models since the nonlinear and iterative nature of the diffusion process renders the posterior intractable.
We propose a variational approach that by design seeks to approximate the true posterior distribution.
arXiv Detail & Related papers (2023-05-07T23:00:47Z) - Diffusion Posterior Sampling for General Noisy Inverse Problems [50.873313752797124]
We extend diffusion solvers to handle noisy (non)linear inverse problems via approximation of the posterior sampling.
Our method demonstrates that diffusion models can incorporate various measurement noise statistics.
arXiv Detail & Related papers (2022-09-29T11:12:27Z) - Improving Diffusion Models for Inverse Problems using Manifold Constraints [55.91148172752894]
We show that current solvers throw the sample path off the data manifold, and hence the error accumulates.
To address this, we propose an additional correction term inspired by the manifold constraint.
We show that our method is superior to the previous methods both theoretically and empirically.
arXiv Detail & Related papers (2022-06-02T09:06:10Z) - Denoising Diffusion Restoration Models [110.1244240726802]
Denoising Diffusion Restoration Models (DDRM) is an efficient, unsupervised posterior sampling method.
We demonstrate DDRM's versatility on several image datasets for super-resolution, deblurring, inpainting, and colorization.
arXiv Detail & Related papers (2022-01-27T20:19:07Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.