<ul><li>Diffusion models have shown strong performances in solving inverse problems through posterior sampling.</li><li>Decoupled Posterior Sampling methods have been proposed to address errors in earlier steps.</li><li>The proposed Guided Decoupled Posterior Sampling (GDPS) method integrates a data consistency constraint in the reverse process.</li><li>Experimental results demonstrate that GDPS achieves state-of-the-art performance, improving accuracy over existing methods.</li></ul>

Improving Decoupled Posterior Sampling for Inverse Problems using Data Consistency Constraint

Discover more