Dynamically Unfolding Recurrent Restorer: A Moving Endpoint Control Method for Image Restoration
arXiv:1805.07709
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.
arXiv commentThe first two authors contributed equally
Cited by in corpus (13)
- A Review on Deep Learning in Medical Image Reconstruction
- Understanding and Improving Transformer From a Multi-Particle Dynamic System Point of View
- Kindling the Darkness: A Practical Low-light Image Enhancer
- You Only Propagate Once: Accelerating Adversarial Training via Maximal Principle
- Developing and Evaluating Deep Neural Network-based Denoising for Nanoparticle TEM Images with Ultra-low Signal-to-Noise
- A Mean-field Analysis of Deep ResNet and Beyond: Towards Provable Optimization Via Overparameterization From Depth
- Graph Signal Restoration Using Nested Deep Algorithm Unrolling
- Tuning-free Plug-and-Play Proximal Algorithm for Inverse Imaging Problems
- Adaptive Denoising via GainTuning
- Disentangled Image Matting
- Learning to Discretize: Solving 1D Scalar Conservation Laws via Deep Reinforcement Learning
- TFPnP: Tuning-free Plug-and-Play Proximal Algorithm with Applications to Inverse Imaging Problems
- LocalNorm: Robust Image Classification through Dynamically Regularized Normalization