mlsanityData to 7 Oct 2026

SURE Guided Posterior Sampling: Trajectory Correction for Diffusion-Based Inverse Problems

arXiv 2512.23232 ↗First posted 29 Dec 2025cs.CVcited by 0

On the map: Diffusion models → Inverse problems and image restoration

Abstract (arXiv)

Diffusion models have emerged as powerful learned priors for solving inverse problems. However, current iterative solving approaches which alternate between diffusion sampling and data consistency steps typically require hundreds or thousands of steps to achieve high quality reconstruction due to accumulated errors. We address this challenge with SURE Guided Posterior Sampling (SGPS), a method that corrects sampling trajectory deviations using Stein's Unbiased Risk Estimate (SURE) gradient updates and PCA based noise estimation. By mitigating noise induced errors during the critical early and middle sampling stages, SGPS enables more accurate posterior sampling and reduces error accumulation. This allows our method to maintain high reconstruction quality with fewer than 100 Neural Function Evaluations (NFEs). Our extensive evaluation across diverse inverse problems demonstrates that SGPS consistently outperforms existing methods at low NFE counts.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models. Builds on 37 of its 55 references that are in the map. First posted on arXiv 29 Dec 2025.

Builds on

37 of 55 references.

Closest ancestors · 13

Same direction, newest first

  1. 2024VISION-XL: High Definition Video Inverse Problem Solver using Latent Image Diffusion Models29 Nov
  2. 2024Variational Diffusion Posterior Sampling with Midpoint Guidance13 Oct
  3. 2024A Survey on Diffusion Models for Inverse Problems30 Sep
  4. 2024Improving Diffusion Inverse Problem Solving with Decoupled Noise Annealing1 Jul
  5. 2024Principled Probabilistic Imaging using Diffusion Models as Plug-and-Play Priors29 May
  6. 2024DMPlug: A Plug-in Method for Solving Inverse Problems with Diffusion Models27 May
  7. 2024Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstruction25 Mar
  8. 2023A Variational Perspective on Solving Inverse Problems with Diffusion Models7 May
  9. 2023Score-Based Diffusion Models as Principled Priors for Inverse Imaging23 Apr
  10. 2023Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse Problems10 Mar
  11. 2022Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model1 Dec
  12. 2022Diffusion Posterior Sampling for General Noisy Inverse Problems29 Sep
1 more
  1. 2022Denoising Diffusion Restoration Models27 Jan

Other references · 24

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2020Denoising Diffusion Implicit Modelscited by 9,655
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  5. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  6. 2022Flow Matching for Generative Modelingcited by 5,426
  7. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  8. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  9. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  10. 2022Video Diffusion Modelscited by 2,280
  11. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,725
  12. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,483
12 more
  1. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,036
  2. 2015Automatic differentiation in machine learning: a surveycited by 846
  3. 2021Solving Inverse Problems in Medical Imaging with Score-Based Generative Modelscited by 514
  4. 2022Latent Video Diffusion Models for High-Fidelity Long Video Generationcited by 385
  5. 2023Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Modelscited by 169
  6. 2022RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generationcited by 162
  7. 2023Manifold Preserving Guided Diffusioncited by 153
  8. 2022Gradients without Backpropagationcited by 73
  9. 2021Explore Image Deblurring via Blur Kernel Spacecited by 58
  10. 2019Uncertainty Quantification in Deep MRI Reconstructioncited by 49
  11. 2018Unsupervised Learning with Stein's Unbiased Risk Estimatorcited by 47
  12. 2024Implicit Image-to-Image Schrodinger Bridge for Image Restorationcited by 13

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Posterior Continuation with Noise-Conditioned Frequency Exposure for Diffusion Inverse Problems
  2. 2025Solving Diffusion Inverse Problems with Restart Posterior Sampling
  3. 2026Beyond Accuracy: Evaluating Posterior Fidelity of Diffusion Inverse Solvers
  4. 2024Enhancing Diffusion Posterior Sampling for Inverse Problems by Integrating Crafted Measurements
  5. 2024Improving Decoupled Posterior Sampling for Inverse Problems using Data Consistency Constraint
  6. 2025Guided Diffusion Sampling on Function Spaces with Applications to PDEs
  7. 2026Noise-Adaptive Diffusion Sampling for Inverse Problems Without Task-Specific Tuning
  8. 2024Zero-Shot Adaptation for Approximate Posterior Sampling of Diffusion Models in Inverse Problems