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

2018/05/20 by Xiaoshuai Zhang, Yiping Lu, Zhang, Xiaoshuai +5 · 4 citations
Computer Science · #Advanced Image Processing Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image and Signal Denoising Methods #Image and Video Quality Assessment

paper · pdf · doi:10.48550/arxiv.1805.07709

openalex publication_date 2018/05/20 · openalex created_date 2019/07/30 · openalex updated_date 2026/07/28

Abstract

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

Cited by

• TFPnP: Tuning-free Plug-and-Play Proximal Algorithm with Applications to Inverse Imaging Problems
• You Only Propagate Once: Accelerating Adversarial Training via Maximal\n Principle
• Disentangled Image Matting
• Tuning-free Plug-and-Play Proximal Algorithm for Inverse Imaging Problems

Related

• DRM-IR: Task-Adaptive Deep Unfolding Network for All-In-One Image Restoration
• Restoring Images with Unknown Degradation Factors by Recurrent Use of a Multi-branch Network
• Restorer: Removing Multi-Degradation with All-Axis Attention and Prompt Guidance
• Crafting a Toolchain for Image Restoration by Deep Reinforcement Learning
• ControlMambaIR: Conditional Controls with State-Space Model for Image Restoration