Equivariant Denoisers for Image Restoration
This addresses image restoration for computer vision applications, but it appears incremental as it builds on existing Plug-and-Play paradigms with equivariance properties.
The paper tackled the problem of image restoration by leveraging equivariant denoisers to encode invariant image priors, resulting in a unified framework called Equivariant Regularization by Denoising (ERED) with analyzed convergence and practical benefits.
One key ingredient of image restoration is to define a realistic prior on clean images to complete the missing information in the observation. State-of-the-art restoration methods rely on a neural network to encode this prior. Moreover, typical image distributions are invariant to some set of transformations, such as rotations or flips. However, most deep architectures are not designed to represent an invariant image distribution. Recent works have proposed to overcome this difficulty by including equivariance properties within a Plug-and-Play paradigm. In this work, we propose a unified framework named Equivariant Regularization by Denoising (ERED) based on equivariant denoisers and stochastic optimization. We analyze the convergence of this algorithm and discuss its practical benefit.