Dynamically unfolding recurrent restorer: A moving endpoint control method for image restoration

In this paper, we propose a new control framework called the moving endpoint control to restore images corrupted by different degradation levels using a single model. The proposed control problem contains an image restoration dynamic which is modeled by a convolutional RNN. The moving endpoint, which is essentially the terminal time of the associated dynamic, 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.