Diffusion Posterior Sampling for General Noisy Inverse Problems

Abstract

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 solving simple linear inverse problems in noiseless settings, which significantly under-represents the complexity of real-world problems. In this work, we extend diffusion solvers to efficiently handle general noisy (non)linear inverse problems via approximation of the posterior sampling. Interestingly, the resulting posterior sampling scheme is a blended version of diffusion sampling with the manifold constrained gradient without a strict measurement consistency projection step, yielding a more desirable generative path in noisy settings compared to the previous studies. Our method demonstrates that diffusion models can incorporate various measurement noise statistics such as Gaussian and Poisson, and also efficiently handle noisy nonlinear inverse problems such as Fourier phase retrieval and non-uniform deblurring. Code available at https://github.com/DPS2022/diffusion-posterior-sampling

ICLR 2023 spotlight

Cited by in corpus (18)

• Diffusion Models, Image Super-Resolution And Everything: A Survey
• A Review on Low-Dose Emission Tomography Post-Reconstruction Denoising with Neural Network Approaches
• Systematic Review on Learning-based Spectral CT
• Conditional score-based diffusion models for solving inverse problems in mechanics
• Fast Diffusion EM: a diffusion model for blind inverse problems with application to deconvolution
• Score-Based Generative Models for PET Image Reconstruction
• 3DGR-CT: Sparse-View CT Reconstruction with a 3D Gaussian Representation
• ElasticDiffusion: Training-free Arbitrary Size Image Generation through Global-Local Content Separation
• Probing the Limits and Capabilities of Diffusion Models for the Anatomic Editing of Digital Twins
• DRUM: Diffusion-based runoff model for probabilistic flood forecasting
• Score-Based Diffusion Models for Photoacoustic Tomography Image Reconstruction
• Reflection-Equivariant Diffusion for 3D Structure Determination from Isotopologue Rotational Spectra in Natural Abundance
• Diffusion-Based Audio Inpainting
• Robust multi-coil MRI reconstruction via self-supervised denoising
• Equivariant Bootstrapping for Uncertainty Quantification in Imaging Inverse Problems
• Monte Carlo guided Diffusion for Bayesian linear inverse problems
• Adapt and Diffuse: Sample-adaptive Reconstruction via Latent Diffusion Models
• Equivariant plug-and-play image reconstruction