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


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.

Resources

  • Paper: [PDF]
  • Supplementary Materials: [PDF]
  • Posters: [Poster 1] [Poster 2 (soon)]
  • Code: [GitHub]
  • Citation

    @inproceedings{ zhang2018dynamically, title={Dynamically Unfolding Recurrent Restorer: A Moving Endpoint Control Method for Image Restoration}, author={Xiaoshuai Zhang and Yiping Lu and Jiaying Liu and Bin Dong}, booktitle={International Conference on Learning Representations}, year={2019}, url={https://openreview.net/forum?id=SJfZKiC5FX}, }