Saved in:
Bibliographic Details
Main Authors: Hen, Liav, Tirer, Tom, Giryes, Raja, Abu-Hussein, Shady
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.18471
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910080867237888
author Hen, Liav
Tirer, Tom
Giryes, Raja
Abu-Hussein, Shady
author_facet Hen, Liav
Tirer, Tom
Giryes, Raja
Abu-Hussein, Shady
contents 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 demonstrate that these approaches differ fundamentally in their treatment of the diffusion denoiser's Jacobian within the likelihood term. While this Jacobian encodes critical prior knowledge of the data distribution, training-induced non-idealities can degrade performance in zero-shot settings. In this work, we bridge direct and proximal approaches by proposing a principled Jacobian-Aware Posterior Sampler (JAPS). JAPS leverages the Jacobian's prior knowledge while mitigating its detrimental effects through a corresponding proximal solution, requiring no additional computational cost. Our method enhances reconstruction quality across diverse linear and nonlinear noisy imaging tasks, outperforming existing diffusion-based baselines in perceptual quality while maintaining or improving distortion metrics.
format Preprint
id arxiv_https___arxiv_org_abs_2511_18471
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Jacobian-aware Posterior Sampling for Inverse Problems
Hen, Liav
Tirer, Tom
Giryes, Raja
Abu-Hussein, Shady
Computer Vision and Pattern Recognition
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 demonstrate that these approaches differ fundamentally in their treatment of the diffusion denoiser's Jacobian within the likelihood term. While this Jacobian encodes critical prior knowledge of the data distribution, training-induced non-idealities can degrade performance in zero-shot settings. In this work, we bridge direct and proximal approaches by proposing a principled Jacobian-Aware Posterior Sampler (JAPS). JAPS leverages the Jacobian's prior knowledge while mitigating its detrimental effects through a corresponding proximal solution, requiring no additional computational cost. Our method enhances reconstruction quality across diverse linear and nonlinear noisy imaging tasks, outperforming existing diffusion-based baselines in perceptual quality while maintaining or improving distortion metrics.
title Jacobian-aware Posterior Sampling for Inverse Problems
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.18471