PixelRL: Fully Convolutional Network With Reinforcement Learning for Image Processing
PixelRL: Fully Convolutional Network With Reinforcement Learning for Image Processing
复制标题
DOI：
10.1109/tmm.2019.2960636
复制
发表时间：
2020-07-01
影响因子：
7.3
通讯作者：
Yamasaki, Toshihiko
中科院分区：
文献类型：
--
作者：
Furuta, Ryosuke;Inoue, Naoto;Yamasaki, Toshihiko
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，深度强化学习（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。所提出的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。此外，可以可视化在每次迭代时对每个像素采用什么样的操作，这将有助于我们理解为什么以及如何选择这样的操作。我们还相信，我们的技术可以增强深度神经网络的可解释性和可解释性。此外，由于在每个像素处执行的操作是可视化的，因此我们可以在必要时更改或修改操作。我们将所提出的方法应用于各种图像处理任务：图像去噪，图像恢复，局部颜色增强和显着性驱动的图像编辑。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。源代码可在https://github.com/rfuruta/pixelRL上获得。
This article 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 reinforcement learning (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. Besides, it is possible to visualize what kind of operation is employed for each pixel at each iteration, which would help us understand why and how such an operation is chosen. We also believe that our technology can enhance the explainability and interpretability of the deep neural networks. In addition, because the operations executed at each pixels are visualized, we can change or modify the operations if necessary. We apply the proposed method to a variety of image processing tasks: image denoising, image restoration, local color enhancement, and saliency-driven image editing. 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. The source code is available on https://github.com/rfuruta/pixelRL.