Proximal Splitting Networks for Image Restoration

03/17/2019
by   Raied Aljadaany, et al.
0

Image restoration problems are typically ill-posed requiring the design of suitable priors. These priors are typically hand-designed and are fully instantiated throughout the process. In this paper, we introduce a novel framework for handling inverse problems related to image restoration based on elements from the half quadratic splitting method and proximal operators. Modeling the proximal operator as a convolutional network, we defined an implicit prior on the image space as a function class during training. This is in contrast to the common practice in literature of having the prior to be fixed and fully instantiated even during training stages. Further, we allow this proximal operator to be tuned differently for each iteration which greatly increases modeling capacity and allows us to reduce the number of iterations by an order of magnitude as compared to other approaches. Our final network is an end-to-end one whose run time matches the previous fastest algorithms while outperforming them in recovery fidelity on two image restoration tasks. Indeed, we find our approach achieves state-of-the-art results on benchmarks in image denoising and image super resolution while recovering more complex and finer details.

READ FULL TEXT

page 2

page 3

page 5

page 8

research
10/19/2022

Provably Convergent Plug Play Linearized ADMM, applied to Deblurring Spatially Varying Kernels

Plug Play methods combine proximal algorithms with denoiser priors t...
research
07/03/2020

End-to-end Interpretable Learning of Non-blind Image Deblurring

Non-blind image deblurring is typically formulated as a linear least-squ...
research
07/26/2016

Generic 3D Convolutional Fusion for image restoration

Also recently, exciting strides forward have been made in the area of im...
research
02/15/2021

Plug-and-Play external and internal priors for image restoration

Image restoration problems were traditionally formulated as the minimiza...
research
03/29/2017

Image Restoration using Autoencoding Priors

We propose to leverage denoising autoencoder networks as priors to addre...
research
12/11/2018

Deep Unfolding of a Proximal Interior Point Method for Image Restoration

Variational methods are widely applied to ill-posed inverse problems for...
research
11/27/2017

Recurrent Generative Adversarial Networks for Proximal Learning and Automated Compressive Image Recovery

Recovering images from undersampled linear measurements typically leads ...

Please sign up or login with your details

Forgot password? Click here to reset