Plug-and-play ISTA converges with kernel denoisers

Abstract

Plug-and-play (PnP) method is a recent paradigm for image regularization, where the proximal operator (associated with some given regularizer) in an iterative algorithm is replaced with a powerful denoiser. Algorithmically, this involves repeated inversion (of the forward model) and denoising until convergence. Remarkably, PnP regularization produces promising results for several restoration applications. However, a fundamental question in this regard is the theoretical convergence of the PnP iterations, since the algorithm is not strictly derived from an optimization framework. This question has been investigated in recent works, but there are still many unresolved problems. For example, it is not known if convergence can be guaranteed if we use generic kernel denoisers (e.g. nonlocal means) within the ISTA framework (PnP-ISTA). We prove that, under reasonable assumptions, fixed-point convergence of PnP-ISTA is indeed guaranteed for linear inverse problems such as deblurring, inpainting and superresolution (the assumptions are verifiable for inpainting). We compare our theoretical findings with existing results, validate them numerically, and explain their practical relevance.

arXiv comment5 pages, Accepted to IEEE Signal Processing Letters

References in corpus (7)

• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Fast Image Recovery Using Variable Splitting and Constrained Optimization
• Denoising Prior Driven Deep Neural Network for Image Restoration
• Plug-and-Play Priors for Bright Field Electron Tomography and Sparse Interpolation
• Learning Proximal Operators: Using Denoising Networks for Regularizing Inverse Imaging Problems
• An Online Plug-and-Play Algorithm for Regularized Image Reconstruction
• Plug-and-Play Methods Provably Converge with Properly Trained Denoisers

Cited by in corpus (8)

• Learning to Optimize: A Primer and A Benchmark
• Provable Convergence of Plug-and-Play Priors with MMSE denoisers
• Fixed-Point and Objective Convergence of Plug-and-Play Algorithms
• On Plug-and-Play Regularization using Linear Denoisers
• Gradient Step Denoiser for convergent Plug-and-Play
• Plug-and-Play Regularization using Linear Solvers
• On the Contractivity of Plug-and-Play Operators
• Provably Convergent Plug & Play Linearized ADMM, applied to Deblurring Spatially Varying Kernels