paper-with-me

Papers

Score-Based Diffusion Models as Principled Priors for Inverse Imaging

2023-04-23 · ICCV 2023 1 · Berthy T. Feng, Jamie Smith, Michael Rubinstein, Huiwen Chang, Katherine L. Bouman, William T. Freeman

Priors are essential for reconstructing images from noisy and/or incomplete measurements. The choice of the prior determines both the quality and uncertainty of recovered images. We propose turning score-based diffusion models into principled image priors ("score-based priors") for analyzing a posterior of images given measurements. Previously, probabilistic priors were limited to handcrafted regularizers and simple distributions. In this work, we empirically validate the theoretically-proven probability function of a score-based diffusion model. We show how to sample from resulting posteriors by using this probability function for variational inference. Our results, including experiments on denoising, deblurring, and interferometric imaging, suggest that score-based priors enable principled inference with a sophisticated, data-driven image prior.

📄 PDF Abstract BibTeX arXiv:2304.11751

Code (1)

berthyf96/score_prior jax

Tasks

DeblurringDenoisingVariational Inference

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

Variational Bayesian Imaging with an Efficient Surrogate Score-based Prior

2023-09-05 · Berthy T. Feng, Katherine L. Bouman

We propose a surrogate function for efficient yet principled use of score-based priors in Bayesian imaging. We consider ill-posed inverse imaging problems in which one aims for a clean image posterior given incomplete or…

Variational Inference

Whitened Score Diffusion: A Structured Prior for Imaging Inverse Problems

2025-05-15 · Jeffrey Alido, Tongyu Li, Yu Sun, Lei Tian

Conventional score-based diffusion models (DMs) may struggle with anisotropic Gaussian diffusion processes due to the required inversion of covariance matrices in the denoising score matching training objective \cite{vin…

Denoising

Learning Diffusion Model from Noisy Measurement using Principled Expectation-Maximization Method

2024-10-15 · Weimin Bai, Weiheng Tang, Enze Ye, Siyi Chen 외

Diffusion models have demonstrated exceptional ability in modeling complex image distributions, making them versatile plug-and-play priors for solving imaging inverse problems. However, their reliance on large-scale clea…

DeblurringDenoising

Principled Probabilistic Imaging using Diffusion Models as Plug-and-Play Priors

2024-05-29 · Zihui Wu, Yu Sun, Yifan Chen, Bingliang Zhang 외

Diffusion models (DMs) have recently shown outstanding capabilities in modeling complex image distributions, making them expressive image priors for solving Bayesian inverse problems. However, most existing DM-based meth…

Image DeblurringImage Super-Resolution

Provably Accelerated Imaging with Restarted Inertia and Score-based Image Priors

2025-10-08 · Marien Renaud, Julien Hermant, Deliang Wei, Yu Sun arxiv

Fast convergence and high-quality image recovery are two essential features of algorithms for solving ill-posed imaging inverse problems. Existing methods, such as regularization by denoising (RED), often focus on design…