HIRL: Hybrid Image Restoration Based on Hierarchical Deep Reinforcement Learning via Two-Step Analysis
Xiaoyu Zhang, Wei Gao
Abstract
The restoration of hybrid distorted images in real-world scenarios is still a difficult problem due to the fact that the degrading types and degrees are always unknown. Previous studies typically utilize multiple recovery tools to restore images. However, each tool adopted inevitably introduces additional noise and will affect the subsequent recovery results. To address this issue, in this paper, we propose a hierarchical deep reinforcement learning framework (HIRL), which balance both benefits and noises brought by each tool and select the appropriate type and degree tools. The proposed method endeavors to find a long-term optimal tool sequence, which is better than the greedy strategy that employs the tools with the largest short-term returns. Meanwhile, it benefits from a hierarchical design to reduce time consumption and complexity compared to a brute force strategy. Experiments demonstrate the superiority of the proposed method over other state-of-the-art methods. Furthermore, our framework is highly scalable and can be easily extended to the other recovery pipelines.