JE2NET: Joint Exploitation and Exploration in Reinforcement Learning Based Image Restoration

Previous reinforcement learning (RL) based image restoration studies typically train RL agents to search for recovery tools from a constructed toolset and iteratively recover images. However, we argue that these agents rely on pre-trained RL models with fixed-length paths for restoration, which performs poorly in the case of unknown distortions. To address these issues, we propose a joint exploitation and exploration reinforcement learning network (JE²Net). Specifically, we propose a new deep classification network for image feature extraction and tool selection, which serves as a model prior. Second, we design a stochastic strategy to randomly select tools and a dynamic termination strategy to adaptively stop the recovery process. In this way, the model prior and exploration mechanism can be jointly used to expand the search space and obtain more quality gain. Experimental results show that our proposed method is more flexible compared to other state-of-the-art methods and achieves significant quality improvements in the presence of unknown distortions.