ReGuidance: A Simple Diffusion Wrapper for Boosting Sample Quality on Hard Inverse Problems

• URL: http://arxiv.org/abs/2506.10955v1
• Date: Thu, 12 Jun 2025 17:55:17 GMT
• Title: ReGuidance: A Simple Diffusion Wrapper for Boosting Sample Quality on Hard Inverse Problems
• Authors: Aayush Karan, Kulin Shah, Sitan Chen,
• Abstract summary: We devise a simple wrapper, ReGuidance, for boosting both the sample realism and reward achieved by training-free methods.<n>We evaluate our wrapper on hard inverse problems like large box in-painting and super-resolution with high upscaling.
• Score: 10.698572109242434
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: There has been a flurry of activity around using pretrained diffusion models as informed data priors for solving inverse problems, and more generally around steering these models using reward models. Training-free methods like diffusion posterior sampling (DPS) and its many variants have offered flexible heuristic algorithms for these tasks, but when the reward is not informative enough, e.g., in hard inverse problems with low signal-to-noise ratio, these techniques veer off the data manifold, failing to produce realistic outputs. In this work, we devise a simple wrapper, ReGuidance, for boosting both the sample realism and reward achieved by these methods. Given a candidate solution $\hat{x}$ produced by an algorithm of the user's choice, we propose inverting the solution by running the unconditional probability flow ODE in reverse starting from $\hat{x}$, and then using the resulting latent as an initialization for DPS. We evaluate our wrapper on hard inverse problems like large box in-painting and super-resolution with high upscaling. Whereas state-of-the-art baselines visibly fail, we find that applying our wrapper on top of these baselines significantly boosts sample quality and measurement consistency. We complement these findings with theory proving that on certain multimodal data distributions, ReGuidance simultaneously boosts the reward and brings the candidate solution closer to the data manifold. To our knowledge, this constitutes the first rigorous algorithmic guarantee for DPS.

Related papers

• Distributional Diffusion Models with Scoring Rules [83.38210785728994]
  Diffusion models generate high-quality synthetic data.<n> generating high-quality outputs requires many discretization steps.<n>We propose to accomplish sample generation by learning the posterior em distribution of clean data samples.
  arXiv  Detail & Related papers  (2025-02-04T16:59:03Z)
• Think Twice Before You Act: Improving Inverse Problem Solving With MCMC [40.5682961122897]
  We propose textbfDiffusion textbfPosterior textbfMCMC (textbfDPMC) to solve inverse problems with pretrained diffusion models. Our algorithm outperforms DPS with less number of evaluations across nearly all tasks, and is competitive among existing approaches.
  arXiv  Detail & Related papers  (2024-09-13T06:10:54Z)
• Diffusion Prior-Based Amortized Variational Inference for Noisy Inverse Problems [12.482127049881026]
  We propose a novel approach to solve inverse problems with a diffusion prior from an amortized variational inference perspective. Our amortized inference learns a function that directly maps measurements to the implicit posterior distributions of corresponding clean data, enabling a single-step posterior sampling even for unseen measurements.
  arXiv  Detail & Related papers  (2024-07-23T02:14:18Z)
• Fast Samplers for Inverse Problems in Iterative Refinement Models [19.099632445326826]
  We propose a plug-and-play framework for constructing efficient samplers for inverse problems. Our method can generate high-quality samples in as few as 5 conditional sampling steps and outperforms competing baselines requiring 20-1000 steps.
  arXiv  Detail & Related papers  (2024-05-27T21:50:16Z)
• Divide-and-Conquer Posterior Sampling for Denoising Diffusion Priors [21.0128625037708]
  We present an innovative framework, divide-and-conquer posterior sampling. It reduces the approximation error associated with current techniques without the need for retraining. We demonstrate the versatility and effectiveness of our approach for a wide range of Bayesian inverse problems.
  arXiv  Detail & Related papers  (2024-03-18T01:47:24Z)
• BlindDiff: Empowering Degradation Modelling in Diffusion Models for Blind Image Super-Resolution [52.47005445345593]
  BlindDiff is a DM-based blind SR method to tackle the blind degradation settings in SISR. BlindDiff seamlessly integrates the MAP-based optimization into DMs. Experiments on both synthetic and real-world datasets show that BlindDiff achieves the state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-03-15T11:21:34Z)
• Ambient Diffusion Posterior Sampling: Solving Inverse Problems with Diffusion Models Trained on Corrupted Data [54.09959775518994]
  We provide a framework for solving inverse problems with diffusion models learned from linearly corrupted data.<n>We train diffusion models for MRI with access only to subsampled multi-coil measurements at acceleration factors R= 2,4,6,8.<n>For MRI reconstruction in high acceleration regimes, we observe that A-DPS models trained on subsampled data are better suited to solving inverse problems than models trained on fully sampled data.
  arXiv  Detail & Related papers  (2024-03-13T17:28:20Z)
• Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency [7.671153315762146]
  Training diffusion models in the pixel space are both data-intensive and computationally demanding. Latent diffusion models, which operate in a much lower-dimensional space, offer a solution to these challenges. We propose textitReSample, an algorithm that can solve general inverse problems with pre-trained latent diffusion models.
  arXiv  Detail & Related papers  (2023-07-16T18:42:01Z)
• Plug-and-Play split Gibbs sampler: embedding deep generative priors in Bayesian inference [12.91637880428221]
  This paper introduces a plug-and-play sampling algorithm that leverages variable splitting to efficiently sample from a posterior distribution. It divides the challenging task of posterior sampling into two simpler sampling problems. Its performance is compared to recent state-of-the-art optimization and sampling methods.
  arXiv  Detail & Related papers  (2023-04-21T17:17:51Z)
• Reflected Diffusion Models [93.26107023470979]
  We present Reflected Diffusion Models, which reverse a reflected differential equation evolving on the support of the data. Our approach learns the score function through a generalized score matching loss and extends key components of standard diffusion models.
  arXiv  Detail & Related papers  (2023-04-10T17:54:38Z)
• Diffusion Model Based Posterior Sampling for Noisy Linear Inverse Problems [14.809545109705256]
  This paper presents a fast and effective solution by proposing a simple closed-form approximation to the likelihood score. For both diffusion and flow-based models, extensive experiments are conducted on various noisy linear inverse problems. Our method demonstrates highly competitive or even better reconstruction performances while being significantly faster than all the baseline methods.
  arXiv  Detail & Related papers  (2022-11-20T01:09:49Z)
• Diffusion Posterior Sampling for General Noisy Inverse Problems [50.873313752797124]
  We extend diffusion solvers to handle noisy (non)linear inverse problems via approximation of the posterior sampling. Our method demonstrates that diffusion models can incorporate various measurement noise statistics.
  arXiv  Detail & Related papers  (2022-09-29T11:12:27Z)
• Improving Diffusion Models for Inverse Problems using Manifold Constraints [55.91148172752894]
  We show that current solvers throw the sample path off the data manifold, and hence the error accumulates. To address this, we propose an additional correction term inspired by the manifold constraint. We show that our method is superior to the previous methods both theoretically and empirically.
  arXiv  Detail & Related papers  (2022-06-02T09:06:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.