Provable Probabilistic Imaging using Score-Based Generative Priors

2023/10/16 by Yu Sun, Zihui Wu, Sun, Yu +7 · 19 citations
Computer Science · Engineering · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Signal Denoising Methods #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #Medical Image Segmentation Techniques #Sparse and Compressive Sensing Techniques #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2310.10835

openalex publication_date 2023/10/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Estimating high-quality images while also quantifying their uncertainty are two desired features in an image reconstruction algorithm for solving ill-posed inverse problems. In this paper, we propose plug-and-play Monte Carlo (PMC) as a principled framework for characterizing the space of possible solutions to a general inverse problem. PMC is able to incorporate expressive score-based generative priors for high-quality image reconstruction while also performing uncertainty quantification via posterior sampling. In particular, we develop two PMC algorithms that can be viewed as the sampling analogues of the traditional plug-and-play priors (PnP) and regularization by denoising (RED) algorithms. To improve the sampling efficiency, we introduce weighted annealing into these PMC algorithms, further developing two additional annealed PMC algorithms (APMC). We establish a theoretical analysis for characterizing the convergence behavior of PMC algorithms. Our analysis provides non-asymptotic stationarity guarantees in terms of the Fisher information, fully compatible with the joint presence of weighted annealing, potentially non-log-concave likelihoods, and imperfect score networks. We demonstrate the performance of the PMC algorithms on multiple representative inverse problems with both linear and nonlinear forward models. Experimental results show that PMC significantly improves reconstruction quality and enables high-fidelity uncertainty quantification.

Cited by

• PSI3D: Plug-and-Play 3D Stochastic Inference with Slice-wise Latent Diffusion Prior
• MRI Super-Resolution with Deep Learning: A Comprehensive Survey
• Bregman geometry-aware split Gibbs sampling for Bayesian Poisson inverse problems
• Blade: A Derivative-free Bayesian Inversion Method using Diffusion Priors
• A Recovery Theory for Diffusion Priors: Deterministic Analysis of the Implicit Prior Algorithm
• Multitask Learning with Stochastic Interpolants
• Injecting Measurement Information Yields a Fast and Noise-Robust Diffusion-Based Inverse Problem Solver
• QUTCC: Quantile Uncertainty Training and Conformal Calibration for Imaging Inverse Problems
• Free-running vs. Synchronous: Single-Photon Lidar for High-flux 3D Imaging
• Exact Conditional Score-Guided Generative Modeling for Amortized Inference in Uncertainty Quantification
• Solving Inverse Problems via Diffusion-Based Priors: An Approximation-Free Ensemble Sampling Approach
• Integrating Intermediate Layer Optimization and Projected Gradient Descent for Solving Inverse Problems with Diffusion Models
• Learning Single Index Models with Diffusion Priors
• Preconditioned Langevin Dynamics with Score-Based Generative Models for Infinite-Dimensional Linear Bayesian Inverse Problems
• PolyMicros: Bootstrapping a Foundation Model for Polycrystalline Material Structure
• Neural Inverse Scattering with Score-based Regularization
• Whitened Score Diffusion: A Structured Prior for Imaging Inverse Problems
• ScoreField: Neural Inverse Scattering with Score-Based Generative Priors
• Unifying and extending Diffusion Models through PDEs for solving Inverse Problems

Related

• Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstruction
• Generative Plug and Play: Posterior Sampling for Inverse Problems
• Denoising Score-Matching for Uncertainty Quantification in Inverse Problems
• Principled Probabilistic Imaging using Diffusion Models as Plug-and-Play Priors
• Bayesian imaging inverse problem with SA-Roundtrip prior via HMC-pCN sampler