← Back to all news
arXiv AI By Zhaoqiang Liu, Tongyao Pang, Ruibing Wang, Yang Zheng

A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors

Read the original on arXiv AI →

The paper introduces a Posterior‑Dynamics Framework that leverages pretrained diffusion models as multiscale priors for linear imaging inverse problems such as deblurring, super‑resolution, and inpainting. By constructing a surrogate likelihood centered on the clean image and incorporating diffusion uncertainty, the authors derive continuous posterior dynamics and a tunable Langevin component for adaptive exploration. They prove theoretical guarantees (endpoint consistency, finite‑horizon tracking, weak accuracy) and present the PD‑IMEX sampler, which achieves high‑quality reconstructions with only 100 score evaluations and controllable fidelity‑diversity trade‑offs.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
Oct 8

Kinetic Langevin Meets Split Gibbs: Accelerated Posterior Sampling for Imaging Inverse Problems with Diffusion Priors

The paper introduces RED-KLwSGS, a new posterior sampling method for Bayesian imaging inverse problems that combines exact Gaussian updates for the data variable with underdamped (kinetic) Langevin diffusion for the auxiliary variable, driven by a one‑shot denoising score. It achieves the same per‑iteration cost as existing Langevin‑within‑SGS samplers while providing non‑asymptotic Wasserstein‑2 convergence guarantees for strongly log‑concave priors. A further variant, Joint-RED-KLwSGS, applies kinetic Langevin diffusion to both variables, and experiments using denoising diffusion probabilistic models on FFHQ and ImageNet demonstrate faster convergence and high‑quality image reconstruction.

By Dai Hai Nguyen, Duc Dung Nguyen
diffusion
More like this →
arXiv AI
Oct 5

Consecutive Posterior Fusion for Diffusive Recovery of Unobservable Image Structures

The paper introduces Consecutive Posterior Fusion Denoising Diffusion Null‑Space Models (CPF‑DDNM), an inference‑time method that fuses successive measurement‑aware estimates to better recover unobservable image structures in severely ill‑posed imaging inverse problems. CPF‑DDNM builds on DDNM’s range/null‑space decomposition, preserving measurement‑determined components while refining prior‑driven null‑space estimates. Experiments on sparse‑view CT, low‑dose CT, and medical image super‑resolution demonstrate consistent improvements over DDNM and competitive performance against other diffusion‑based inverse solvers.

By Elena Morotti, Davide Evangelista, Elena Loli Piccolomini
diffusion
More like this →