Score: 0

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

Published: December 29, 2025 | arXiv ID: 2512.23232v1

By: Minwoo Kim, Hongki Lim

Potential Business Impact:

Fixes blurry pictures faster and better.

Business Areas:
GPS Hardware, Navigation and Mapping

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.

Country of Origin
🇰🇷 Korea, Republic of

Page Count
29 pages

Category
Computer Science:
CV and Pattern Recognition