SURE Guided Posterior Sampling: Trajectory Correction for Diffusion-Based Inverse Problems
By: Minwoo Kim, Hongki Lim
Potential Business Impact:
Fixes blurry pictures faster and better.
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.
Similar Papers
Robust Posterior Diffusion-based Sampling via Adaptive Guidance Scale
CV and Pattern Recognition
Makes blurry pictures sharp and clear.
Guided Path Sampling: Steering Diffusion Models Back on Track with Principled Path Guidance
CV and Pattern Recognition
Makes AI art follow instructions better.
Provable Diffusion Posterior Sampling for Bayesian Inversion
Machine Learning (Stat)
Makes computers learn and guess better from data.