paper-with-me

Papers

DMPlug: A Plug-in Method for Solving Inverse Problems with Diffusion Models

2024-05-27 · Hengkang Wang, Xu Zhang, Taihui Li, Yuxiang Wan, Tiancong Chen, Ju Sun

Pretrained diffusion models (DMs) have recently been popularly used in solving inverse problems (IPs). The existing methods mostly interleave iterative steps in the reverse diffusion process and iterative steps to bring the iterates closer to satisfying the measurement constraint. However, such interleaving methods struggle to produce final results that look like natural objects of interest (i.e., manifold feasibility) and fit the measurement (i.e., measurement feasibility), especially for nonlinear IPs. Moreover, their capabilities to deal with noisy IPs with unknown types and levels of measurement noise are unknown. In this paper, we advocate viewing the reverse process in DMs as a function and propose a novel plug-in method for solving IPs using pretrained DMs, dubbed DMPlug. DMPlug addresses the issues of manifold feasibility and measurement feasibility in a principled manner, and also shows great potential for being robust to unknown types and levels of noise. Through extensive experiments across various IP tasks, including two linear and three nonlinear IPs, we demonstrate that DMPlug consistently outperforms state-of-the-art methods, often by large margins especially for nonlinear IPs. The code is available at https://github.com/sun-umn/DMPlug.

📄 PDF Abstract BibTeX arXiv:2405.16749

Code (1)

sun-umn/dmplug 공식 구현

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

InverseBench: Benchmarking Plug-and-Play Diffusion Priors for Inverse Problems in Physical Sciences

2025-03-14 · Hongkai Zheng, Wenda Chu, Bingliang Zhang, Zihui Wu 외

Plug-and-play diffusion priors (PnPDP) have emerged as a promising research direction for solving inverse problems. However, current studies primarily focus on natural image restoration, leaving the performance of these …

BenchmarkingImage Restoration

Plug-and-Play Posterior Sampling for Blind Inverse Problems

2025-05-28 · Anqi Li, Weijie Gan, Ulugbek S. Kamilov

We introduce Blind Plug-and-Play Diffusion Models (Blind-PnPDM) as a novel framework for solving blind inverse problems where both the target image and the measurement operator are unknown. Unlike conventional methods th…

Blind Image DeblurringDeblurringDenoisingImage Deblurring+1

Fast Samplers for Inverse Problems in Iterative Refinement Models

2024-05-27 · Kushagra Pandey, Ruihan Yang, Stephan Mandt

Constructing fast samplers for unconditional diffusion and flow-matching models has received much attention recently; however, existing methods for solving inverse problems, such as super-resolution, inpainting, or deblu…

DeblurringImage RestorationSuper-Resolution

Investigating the Feasibility of Patch-based Inference for Generalized Diffusion Priors in Inverse Problems for Medical Images

2025-01-25 · Saikat Roy, Mahmoud Mostapha, Radu Miron, Matt Holbrook 외

Plug-and-play approaches to solving inverse problems such as restoration and super-resolution have recently benefited from Diffusion-based generative priors for natural as well as medical images. However, solutions often…

Super-Resolution

PnP-CM: Consistency Models as Plug-and-Play Priors for Inverse Problems

2025-09-25 · Merve Gülle, Junno Yun, Yaşar Utku Alçalar, Mehmet Akçakaya arxiv

Diffusion models have found extensive use in solving inverse problems, by sampling from an approximate posterior distribution of data given the measurements. Recently, consistency models (CMs) have been proposed to direc…