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

TL;DR

This paper introduces DURR, a novel RNN-based control framework that adaptively restores images with varying degradation levels in a single model, achieving state-of-the-art results.

Contribution

The paper presents a new moving endpoint control framework with a policy network for dynamic image restoration, enabling generalization to unseen degradation levels.

Findings

Achieves state-of-the-art performance in blind denoising and JPEG deblocking.

Generalizes well to higher degradation levels not seen during training.

Demonstrates effective adaptive control in image restoration tasks.

Abstract

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.