Preprint

SNaP: One-Step Posterior Sampling for Noisy Inverse Problems

Shirin Shoushtari Edward P. Chandler Xiao Shi U. Kamilov

Sep 2026 · 0 citations · 49 references

Computer Science

TL;DR

SNaP is introduced, a one-step MeanFlow posterior sampler for linear inverse problems with Gaussian noise, which produces diverse, high-quality samples with one network evaluation per draw, 30 to 2250 $\times$ faster than iterative samplers.

Abstract

Diffusion and flow-matching models can produce high-quality posterior samples for inverse problems, but typically require tens to thousands of network evaluations per draw. MeanFlow enables one-step generation, yet applying it to inverse problems leaves no intermediate steps at which to enforce measurement consistency. We introduce SNaP, a one-step MeanFlow posterior sampler for linear inverse problems with Gaussian noise. Its central innovation is a measurement-adapted source: a Gaussian distribution whose mean and anisotropic covariance are determined by the measurement operator, observation, and noise level. The source anchors well-measured directions while preserving variation where the measurements are weak or uninformative. We show that the exact conditional flow transports this source to the true posterior. Across natural-image restoration and multi-coil MRI, SNaP produces diverse, high-quality samples with one network evaluation per draw, 30 to 2250 $\times$ faster than iterative samplers.

arXiv Semantic Scholar

View source

Similar papers

#machine learning Preprint Sep 2026

CLIMB-flow: Coupled Linear Inverse posterior sampling via Multiscale-Based flow

Diffusion models are now widely used in Bayesian inverse problems in imaging as priors, where latent diffusion models are often used for larger scale problems to keep the computational complexity and model-size manageable. Unfortunately, the auto-encoder based compression results in loss of spatial detail. In addition,...

Ze-Qiu Yu, Rui Yuan, Mathews Jacob · 0 citations

Preprint Aug 2026

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

This work defines an explicit surrogate posterior path and derives the Posterior-Dynamics Implicit--Explicit sampler (PD-IMEX), a stable method using one score evaluation per diffusion scale and an implicit data-consistency update, and derives continuous posterior dynamics.

Zhao-Qiang Liu, T. Pang, Ruibing Wang et al. · 1 citation

Preprint Sep 2026

Direct Conditional Transition Sampling for Diffusion Inverse Problems

Training-free diffusion inverse solvers typically choose between local measurement guidance and costly clean-space posterior updates. Independent posterior refresh can improve global correction by sampling a clean conditional and re-noising it, but its practical realization requires probability-flow ODE integration and...

Qi Yu, Han-Lin Wu, Xiao-Hui Sun · 0 citations

Preprint Sep 2026

Residual Diffusion Implicit Models

Diffusion models achieve state-of-the-art results across multiple tasks. However, in inverse problems, standard initialization from pure Gaussian noise misaligns the generative process with real-world degradations. More recent methods such as diffusion bridges impose strict endpoint constraints and often require long r...

J. Guerreiro, Pedro Tomás, Helena Aidos et al. · 0 citations

#machine learning Preprint Sep 2026

PosteriorBench: From Point Estimates to Posterior Matching in Evaluating Generative Inverse Solvers

Generative models are increasingly used to solve scientific inverse problems, but existing evaluations still focus primarily on whether a method can produce a single plausible reconstruction. This is insufficient for ill-posed problems, where multiple solutions may be consistent with the same sparse or noisy observatio...

Jia-Chen Yao, Zi-Siang Hsu, Xi Deng et al. · 0 citations

Preprint Sep 2026

FlowSGS: Improving Flow Matching Priors for Inverse Imaging with Stochastic Interpolants

This work introduces FlowSGS, a flow-based posterior sampling method using Split Gibbs Sampling (SGS) to decompose the posterior into a likelihood step and a prior step and provides a form for the prior step that uses SI's reverse-time SDE, and shows connections to previous PnP methods.

Tianao Li, Xin-Hui Qian, Emma Alexander · 0 citations