Dynamically Unfolding Recurrent Restorer: A Moving Endpoint Control Method for Image Restoration

by   Xiaoshuai Zhang, et al.
Peking University

In this paper, we propose a new control framework called the moving endpoint control to restore images corrupted by different degradation levels in one model. The proposed control problem contains a restoration dynamics which is modeled by an RNN. The moving endpoint, which is essentially the terminal time of the associated dynamics, is determined by a policy network. We call the proposed model the dynamically unfolding recurrent restorer (DURR). Numerical experiments show that DURR is able to achieve state-of-the-art performances on blind image denoising and JPEG image deblocking. Furthermore, DURR can well generalize to images with higher degradation levels that are not included in the training stage.


page 7

page 8

page 13

page 14

page 15

page 16


PromptIR: Prompting for All-in-One Blind Image Restoration

Image restoration involves recovering a high-quality clean image from it...

Recurrent Inference Machines for Solving Inverse Problems

Much of the recent research on solving iterative inference problems focu...

One Size Fits All: Hypernetwork for Tunable Image Restoration

We introduce a novel approach for tunable image restoration that achieve...

Non-blind Image Restoration Based on Convolutional Neural Network

Blind image restoration processors based on convolutional neural network...

Classifying degraded images over various levels of degradation

Classification for degraded images having various levels of degradation ...

Multi-Dimension Modulation for Image Restoration with Dynamic Controllable Residual Learning

Based on the great success of deterministic learning, to interactively c...

Regularized Richardson-Lucy Algorithm for Sparse Reconstruction of Poissonian Images

Restoration of digital images from their degraded measurements has alway...

Please sign up or login with your details

Forgot password? Click here to reset