all AI news
Convergent plug-and-play with proximal denoiser and unconstrained regularization parameter. (arXiv:2311.01216v1 [math.OC])
cs.CV updates on arXiv.org arxiv.org
In this work, we present new proofs of convergence for Plug-and-Play (PnP)
algorithms. PnP methods are efficient iterative algorithms for solving image
inverse problems where regularization is performed by plugging a pre-trained
denoiser in a proximal algorithm, such as Proximal Gradient Descent (PGD) or
Douglas-Rachford Splitting (DRS). Recent research has explored convergence by
incorporating a denoiser that writes exactly as a proximal operator. However,
the corresponding PnP algorithm has then to be run with stepsize equal to $1$.
The stepsize …
algorithm algorithms arxiv convergence gradient image iterative math pnp regularization research work