Crafting a Toolchain for Image Restoration by Deep Reinforcement Learning
We investigate a novel approach for image restoration by reinforcement learning. Unlike existing studies that mostly train a single large network for a specialized task, we prepare a toolbox consisting of small-scale convolutional networks of different complexities and specialized in different tasks. Our method, RL-Restore, then learns a policy to select appropriate tools from the toolbox to progressively restore the quality of a corrupted image. We formulate a step-wise reward function proportional to how well the image is restored at each step to learn the action policy. We also devise a joint learning scheme to train the agent and tools for better performance in handling uncertainty. In comparison to conventional human-designed networks, RL-Restore is capable of restoring images corrupted with complex and unknown distortions in a more parameter-efficient manner using the dynamically formed toolchain.
Code (2)
Tasks
Deep Reinforcement LearningImage Restorationreinforcement-learningReinforcement LearningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
A Toolchain for Comprehensive Audio/Video Analysis Using Deep Learning Based Multimodal Approach (A use case of riot or violent context detection)
In this paper, we present a toolchain for a comprehensive audio/video analysis by leveraging deep learning based multimodal approach. To this end, different specific tasks of Speech to Text (S2T), Acoustic Scene Classifi…
Acoustic Scene ClassificationEvent DetectionImage Captioningobject-detection+4REPNP: Plug-and-Play with Deep Reinforcement Learning Prior for Robust Image Restoration
Image restoration schemes based on the pre-trained deep models have received great attention due to their unique flexibility for solving various inverse problems. In particular, the Plug-and-Play (PnP) framework is a pop…
DeblurringDeep Reinforcement LearningImage DeblurringImage Restoration+3MASSTAR: A Multi-Modal and Large-Scale Scene Dataset with a Versatile Toolchain for Surface Prediction and Completion
Surface prediction and completion have been widely studied in various applications. Recently, research in surface completion has evolved from small objects to complex large-scale scenes. As a result, researchers have beg…
DescriptiveEnhancing Blind Face Restoration through Online Reinforcement Learning
Blind Face Restoration (BFR) encounters inherent challenges in exploring its large solution space, leading to common artifacts like missing details and identity ambiguity in the restored images. To tackle these challenge…
Blind Face RestorationReinforcement LearningSafe Reinforcement Learning for Real-World Engine Control
This work introduces a toolchain for applying Reinforcement Learning (RL), specifically the Deep Deterministic Policy Gradient (DDPG) algorithm, in safety-critical real-world environments. As an exemplary application, tr…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Safe Reinforcement Learning