Fully Convolutional Network with Multi-Step Reinforcement Learning for Image Processing
Fully Convolutional Network with Multi-Step Reinforcement Learning for Image Processing
复制标题
DOI：
10.1609/aaai.v33i01.33013598
复制
发表时间：
2018-11
期刊：
影响因子：
--
通讯作者：
Ryosuke Furuta;Naoto Inoue;T. Yamasaki
中科院分区：
文献类型：
--
作者：
Ryosuke Furuta;Naoto Inoue;T. Yamasaki
本文解决了一个新的问题设置：用于图像处理的像素奖励强化学习（pixelRL）。在引入深度Q网络之后，深度RL取得了巨大的成功。然而，深度RL在图像处理中的应用仍然有限。因此，我们将深度RL扩展到pixelRL，用于各种图像处理应用。在pixelRL中，每个像素都有一个agent，agent通过采取行动来改变像素值。我们还提出了一种有效的pixelRL学习方法，通过不仅考虑自己像素的未来状态，还考虑相邻像素的未来状态，显着提高了性能。该方法可以应用于一些需要逐像素操作的图像处理任务，其中深度RL从未应用过。我们将该方法应用于三个图像处理任务：图像去噪，图像恢复和局部颜色增强。我们的实验结果表明，所提出的方法实现了相当或更好的性能，与国家的最先进的基于监督学习的方法相比。
This paper tackles a new problem setting: reinforcement learning with pixel-wise rewards (pixelRL) for image processing. After the introduction of the deep Q-network, deep RL has been achieving great success. However, the applications of deep RL for image processing are still limited. Therefore, we extend deep RL to pixelRL for various image processing applications. In pixelRL, each pixel has an agent, and the agent changes the pixel value by taking an action. We also propose an effective learning method for pixelRL that significantly improves the performance by considering not only the future states of the own pixel but also those of the neighbor pixels. The proposed method can be applied to some image processing tasks that require pixel-wise manipulations, where deep RL has never been applied.We apply the proposed method to three image processing tasks: image denoising, image restoration, and local color enhancement. Our experimental results demonstrate that the proposed method achieves comparable or better performance, compared with the state-of-the-art methods based on supervised learning.