Crafting a Toolchain for Image Restoration by Deep Reinforcement Learning

Ke Yu, Chao Dong, Liang Lin, Chen Change Loy; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp. 2443-2452

Abstract


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.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Yu_2018_CVPR,
author = {Yu, Ke and Dong, Chao and Lin, Liang and Change Loy, Chen},
title = {Crafting a Toolchain for Image Restoration by Deep Reinforcement Learning},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2018}
}