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...

Full description

Saved in:
Bibliographic Details
Published in2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition pp. 2443 - 2452
Main Authors Yu, Ke, Dong, Chao, Lin, Liang, Loy, Chen Change
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2018
Subjects
Complexity theory
Distortion
Image restoration
Task analysis
Transform coding
Online AccessGet full text

Cover

More Information
Summary: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 stepwise 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 toolchain1.
ISSN:1063-6919
DOI:10.1109/CVPR.2018.00259