Preprint
Aug 2026
Hybrid-Domain Posterior Sampling for Inverse Problems via Latent Flow Matching
This paper proposes Hybrid-Domain Posterior Sampling (HDPS), a decoupled inference framework that disentangles physical measurement consistency from semantic prior modeling, and establishes a new state-of-the-art, successfully recovering the high-frequency structural precision that latent-only solvers inherently discard.
Hongjie Wu, Yiping Xie, Jiancheng Lv
· 0 citations