MMSE denoisers correspond to 1-weakly convex regularizers via upper Moreau envelopes of negative log-marginals, enabling the first sublinear convergence rates for PnP proximal gradient descent.
Plug-and-play priors for model based reconstruction
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2025 2verdicts
UNVERDICTED 2representative citing papers
DICE integrates two-agent consensus equilibrium into diffusion model sampling to enforce both measurement consistency and generative image priors for improved sparse-view CT reconstruction.
citing papers explorer
-
Nonasymptotic Convergence Rates for Plug-and-Play Methods With MMSE Denoisers
MMSE denoisers correspond to 1-weakly convex regularizers via upper Moreau envelopes of negative log-marginals, enabling the first sublinear convergence rates for PnP proximal gradient descent.
-
DICE: Diffusion Consensus Equilibrium for Sparse-view CT Reconstruction
DICE integrates two-agent consensus equilibrium into diffusion model sampling to enforce both measurement consistency and generative image priors for improved sparse-view CT reconstruction.