Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Posterior Information Dynamics of Diffusion Models for Linear Inverse Problems
Xiangming Meng
Diffusion models are widely used as priors for linear inverse problems, yet endpoint quality does not reveal when measurement information enters reverse denoising or how it is allo…
cs.LG2025
SAIP: A Plug-and-Play Scale-adaptive Module in Diffusion-based Inverse Problems
Lingyu Wang, Xiangming Meng
Solving inverse problems with diffusion models has shown promise in tasks such as image restoration. A common approach is to formulate the problem in a Bayesian framework and sampl…
cs.LG2024
Improving Decoupled Posterior Sampling for Inverse Problems using Data Consistency Constraint
Zhi Qi, Shihong Yuan, Yulin Yuan +3
Diffusion models have shown strong performances in solving inverse problems through posterior sampling while they suffer from errors during earlier steps. To mitigate this issue, s…