Learning local regularization for variational image restoration

by   Jean Prost, et al.

In this work, we propose a framework to learn a local regularization model for solving general image restoration problems. This regularizer is defined with a fully convolutional neural network that sees the image through a receptive field corresponding to small image patches. The regularizer is then learned as a critic between unpaired distributions of clean and degraded patches using a Wasserstein generative adversarial networks based energy. This yields a regularization function that can be incorporated in any image restoration problem. The efficiency of the framework is finally shown on denoising and deblurring applications.


Deeply Aggregated Alternating Minimization for Image Restoration

Regularization-based image restoration has remained an active research t...

Structured and Localized Image Restoration

We present a novel approach to image restoration that leverages ideas fr...

Deep Graph Laplacian Regularization

We propose to combine the robustness merit of model-based approaches and...

Learning Generic Diffusion Processes for Image Restoration

Image restoration problems are typical ill-posed problems where the regu...

Space-variant Generalized Gaussian Regularization for Image Restoration

We propose a new space-variant regularization term for variational image...

Local Sparse Approximation for Image Restoration with Adaptive Block Size Selection

In this paper the problem of image restoration (denoising and inpainting...

An Optimal Control Approach to Early Stopping Variational Methods for Image Restoration

We investigate a well-known phenomenon of variational approaches in imag...

Please sign up or login with your details

Forgot password? Click here to reset