paper-with-me

홈 › Papers

Solving Inverse Problems using Diffusion with Fast Iterative Renoising

2025-01-29 · Matt C. Bendel, Saurav K. Shastri, Rizwan Ahmad, Philip Schniter

Imaging inverse problems can be solved in an unsupervised manner using pre-trained diffusion models. In most cases, that involves approximating the gradient of the measurement-conditional score function in the reverse process. Since the approximations produced by existing methods are quite poor, especially early in the reverse process, we propose a new approach that re-estimates and renoises the image several times per diffusion step. Renoising adds carefully shaped colored noise that ensures the pre-trained diffusion model sees white-Gaussian error, in accordance with how it was trained. We demonstrate the effectiveness of our "DDfire" method at 20, 100, and 1000 neural function evaluations on linear inverse problems and phase retrieval.

📄 PDF Abstract BibTeX arXiv:2501.17468

Code (0)

등록된 구현이 없습니다.

Tasks

Retrieval

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

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

Denoising Diffusion Restoration Models

2022-01-27 · Bahjat Kawar, Michael Elad, Stefano Ermon, Jiaming Song

Many interesting tasks in image restoration can be cast as linear inverse problems. A recent family of approaches for solving these problems uses stochastic algorithms that sample from the posterior distribution of natur…

ColorizationDeblurringDenoisingImage Restoration+2

Diffusion Posterior Sampling for General Noisy Inverse Problems

2022-09-29 · Hyungjin Chung, Jeongsol Kim, Michael T. McCann, Marc L. Klasky 외

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 s…

DeblurringRetrieval

Dual Ascent Diffusion for Inverse Problems

2025-05-23 · Minseo Kim, Axel Levy, Gordon Wetzstein

Ill-posed inverse problems are fundamental in many domains, ranging from astrophysics to medical imaging. Emerging diffusion models provide a powerful prior for solving these problems. Existing maximum-a-posteriori (MAP)…

Image Restoration

SURE Guided Posterior Sampling: Trajectory Correction for Diffusion-Based Inverse Problems

2025-12-29 · Minwoo Kim, Hongki Lim arxiv

Diffusion models have emerged as powerful learned priors for solving inverse problems. However, current iterative solving approaches which alternate between diffusion sampling and data consistency steps typically require…

Noise Estimation