A2-RL: Aesthetics Aware Reinforcement Learning for Image Cropping Debang
一 文章的主要任务 本文介绍的是如何用强化学习的方法对图片做美学剪裁 如下图，Input是一张风景图，初始化是整张图片，然后经过多个action后，我们得到了最后的裁剪方案作为输出。 二 相关的工作 对于图片的裁剪，主要有两个大方向： 基于Attention-based: 这个的目的是在原图中寻找关键区域。比如说在图片上寻找信息量最大的区域等等 基于Aethetics-based: 即基于美学，这
相关文章
- 1. Image Cption：Curiosity-driven Reinforcement Learning for Diverse Visual Paragraph Generation
- 2. Listwise View Ranking for Image Cropping论文理解
- 3. Searching Learning Strategy with Reinforcement Learning for 3D Medical Image Segmentation
- 4. Seam Carving for Content-Aware Image Resizing
- 5. Latent Space Policies for Hierarchical Reinforcement Learning
- 6. Deep Reinforcement Learning for Dialogue Generation
- 7. Deep Reinforcement Learning for Join Order Enumeration
- 8. Deep Reinforcement Learning for List-wise Recommendations
- 9. Application of Opposition-Based Reinforcement Learning in Image Segmentation
- 10. Context-Aware U-Net for Biomedical Image Segmentation
- 更多相关文章...
- • RSS
元素 - RSS 教程 - • ASP.NET Image 控件 - ASP.NET 教程
- • Java Agent入门实战（三）-JVM Attach原理与使用
- • Java Agent入门实战（一）-Instrumentation介绍与使用
相关标签/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
欢迎关注本站公众号,获取更多信息
相关文章
- 1. Image Cption：Curiosity-driven Reinforcement Learning for Diverse Visual Paragraph Generation
- 2. Listwise View Ranking for Image Cropping论文理解
- 3. Searching Learning Strategy with Reinforcement Learning for 3D Medical Image Segmentation
- 4. Seam Carving for Content-Aware Image Resizing
- 5. Latent Space Policies for Hierarchical Reinforcement Learning
- 6. Deep Reinforcement Learning for Dialogue Generation
- 7. Deep Reinforcement Learning for Join Order Enumeration
- 8. Deep Reinforcement Learning for List-wise Recommendations
- 9. Application of Opposition-Based Reinforcement Learning in Image Segmentation
- 10. Context-Aware U-Net for Biomedical Image Segmentation