SURE Guided Posterior Sampling: Trajectory Correction for Diffusion-Based Inverse Problems
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908737090879488 |
|---|---|
| author | Kim, Minwoo Lim, Hongki |
| author_facet | Kim, Minwoo Lim, Hongki |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_23232 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SURE Guided Posterior Sampling: Trajectory Correction for Diffusion-Based Inverse Problems Kim, Minwoo Lim, Hongki Computer Vision and Pattern Recognition 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. |
| title | SURE Guided Posterior Sampling: Trajectory Correction for Diffusion-Based Inverse Problems |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.23232 |