On Maximum-a-Posteriori estimation with Plug & Play priors and stochastic gradient descent

Abstract

Bayesian methods to solve imaging inverse problems usually combine an explicit data likelihood function with a prior distribution that explicitly models expected properties of the solution. Many kinds of priors have been explored in the literature, from simple ones expressing local properties to more involved ones exploiting image redundancy at a non-local scale. In a departure from explicit modelling, several recent works have proposed and studied the use of implicit priors defined by an image denoising algorithm. This approach, commonly known as Plug & Play (PnP) regularisation, can deliver remarkably accurate results, particularly when combined with state-of-the-art denoisers based on convolutional neural networks. However, the theoretical analysis of PnP Bayesian models and algorithms is difficult and works on the topic often rely on unrealistic assumptions on the properties of the image denoiser. This papers studies maximum-a-posteriori (MAP) estimation for Bayesian models with PnP priors. We first consider questions related to existence, stability and well-posedness, and then present a convergence proof for MAP computation by PnP stochastic gradient descent (PnP-SGD) under realistic assumptions on the denoiser used. We report a range of imaging experiments demonstrating PnP-SGD as well as comparisons with other PnP schemes.

References in corpus (9)

• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising
• Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration
• Plug-and-Play Priors for Bright Field Electron Tomography and Sparse Interpolation
• DeepISP: Towards Learning an End-to-End Image Processing Pipeline
• Plug and play methods for magnetic resonance imaging (long version)
• Learning Proximal Operators: Using Denoising Networks for Regularizing Inverse Imaging Problems
• An Online Plug-and-Play Algorithm for Regularized Image Reconstruction
• Fixed-Point and Objective Convergence of Plug-and-Play Algorithms

Cited by in corpus (1)

• Deep Model-Based Super-Resolution with Non-uniform Blur