【24h】

A2-RL: Aesthetics Aware Reinforcement Learning for Image Cropping

机译:A2-RL:用于图像裁剪的审美意识增强学习

获取原文

摘要

Image cropping aims at improving the aesthetic quality of images by adjusting their composition. Most weakly supervised cropping methods (without bounding box supervision) rely on the sliding window mechanism. The sliding window mechanism requires fixed aspect ratios and limits the cropping region with arbitrary size. Moreover, the sliding window method usually produces tens of thousands of windows on the input image which is very time-consuming. Motivated by these challenges, we firstly formulate the aesthetic image cropping as a sequential decision-making process and propose a weakly supervised Aesthetics Aware Reinforcement Learning (A2-RL) framework to address this problem. Particularly, the proposed method develops an aesthetics aware reward function which especially benefits image cropping. Similar to human's decision making, we use a comprehensive state representation including both the current observation and the historical experience. We train the agent using the actor-critic architecture in an end-to-end manner. The agent is evaluated on several popular unseen cropping datasets. Experiment results show that our method achieves the state-of-the-art performance with much fewer candidate windows and much less time compared with previous weakly supervised methods.
机译:图像裁切旨在通过调整图像的构图来提高图像的美学质量。最弱监督的裁剪方法(无边界框监督)依赖于滑动窗口机制。滑动窗口机制需要固定的纵横比,并以任意大小限制裁剪区域。此外,滑动窗口方法通常在输入图像上产生数万个窗口,这非常耗时。受这些挑战的驱使,我们首先将审美图像裁剪公式化为顺序决策过程,并提出了一个弱监督的美学意识强化学习(A2-RL)框架来解决此问题。特别地,所提出的方法开发出特别是图像裁剪的美学意识奖励功能。与人类的决策类似,我们使用全面的状态表示形式,包括当前的观察结果和历史经验。我们以行为者批判的架构以端到端的方式训练代理。在几种流行的看不见的种植数据集上评估了该代理。实验结果表明,与以前的弱监督方法相比,我们的方法以更少的候选窗口和更少的时间实现了最新的性能。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

联系方式:18141920177 (微信同号)

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号