Jacobian-aware Posterior Sampling for Inverse Problems

ArXi:2511.18471v2 Announce Type: replace Diffusion models provide powerful generative priors for solving inverse problems by sampling from a posterior distribution conditioned on corrupted measurements. Existing methods primarily follow two paradigms: direct methods, which approximate the likelihood term, and proximal methods, which incorporate intermediate solutions satisfying measurement constraints into the sampling process. We nstrate that these approaches differ fundamentally in their treatment of the diffusion denoiser's Jacobian within the likelihood term.