A Fast Stochastic Plug-and-Play ADMM for Imaging Inverse Problems
This work addresses a computational bottleneck in imaging applications, offering an incremental improvement for researchers in computational imaging.
The paper tackles the computational expense of frequent denoiser computations in stochastic plug-and-play methods for imaging inverse problems by proposing a new stochastic PnP-ADMM algorithm, achieving improved efficiency and demonstrating effectiveness compared to state-of-the-art methods.
In this work we propose an efficient stochastic plug-and-play (PnP) algorithm for imaging inverse problems. The PnP stochastic gradient descent methods have been recently proposed and shown improved performance in some imaging applications over standard deterministic PnP methods. However, current stochastic PnP methods need to frequently compute the image denoisers which can be computationally expensive. To overcome this limitation, we propose a new stochastic PnP-ADMM method which is based on introducing stochastic gradient descent inner-loops within an inexact ADMM framework. We provide the theoretical guarantee on the fixed-point convergence for our algorithm under standard assumptions. Our numerical results demonstrate the effectiveness of our approach compared with state-of-the-art PnP methods.