<ul data-eligibleForWebStory="false"><li>Plug-and-Play (PnP) algorithms combine a physical model and deep neural network for image restoration.</li><li>PnP algorithms previously used denoisers on less noisy images, contrary to Diffusion Models.</li><li>SNORE is a new PnP framework that applies denoising on images with suitable noise levels.</li><li>SNORE uses stochastic regularization in a gradient descent algorithm for solving inverse problems.</li><li>The algorithm's convergence analysis and annealing extension are provided.</li><li>SNORE is competitive with state-of-the-art methods for deblurring and inpainting tasks.</li></ul>

Plug-and-Play image restoration with Stochastic deNOising REgularization

Discover more