Noise, Denoise, Correct: MCMC Posterior Sampling with Diffusion Priors in Three Steps

Pretrained diffusion models are powerful priors for inverse problems, but posterior sampling under nonlinear, non-differentiable forward models remain hard. We introduce diffusion waltz, an MCMC method using SDEdit-style noising–denoising as a proposal, corrected via Metropolis–Hastings for exact posterior sampling without prior evaluation. We further propose injecting observations into the proposal while preserving exactness, using a gradient-free ensemble Kalman update. On a non-differentiable Navier–Stokes initial condition recovery task, diffusion waltz outperforms existing baselines across different noise and nonlinearity regimes.