论文标题
将确定性注入随机性：重新思考深层图像垫子的构图样式
Infusing Definiteness into Randomness: Rethinking Composition Styles for Deep Image Matting
论文作者
论文摘要
我们研究了深图像垫子中的组成方式，该概念是关于如何利用有限的前景和随机背景以形成训练数据集的数据生成流。先前的艺术以完全随机的方式执行这种流程，只需浏览前景池或在前靠背构图之前将两个前景组合在一起即可。在这项工作中，我们首先表明天真的前景组合可能是有问题的，因此可以得出合理结合前景的替代配方。我们的第二个贡献是观察到，在训练过程中，均可受益于联合前景及其相关源前景的一定发生频率。受此启发的启发，我们引入了一种新颖的构图样式，该样式绑定了源头，并将前景结合在一起。此外，我们还发现，前景组合的不同顺序导致了不同的前景模式，这进一步激发了基于四倍的构图样式。在四个基线基线的受控实验下的结果表明，我们的构图样式的表现优于现有的，并邀请合成数据集和现实世界数据集对一致的性能提高。代码可用：https：//github.com/coconuthust/composition_styles
We study the composition style in deep image matting, a notion that characterizes a data generation flow on how to exploit limited foregrounds and random backgrounds to form a training dataset. Prior art executes this flow in a completely random manner by simply going through the foreground pool or by optionally combining two foregrounds before foreground-background composition. In this work, we first show that naive foreground combination can be problematic and therefore derive an alternative formulation to reasonably combine foregrounds. Our second contribution is an observation that matting performance can benefit from a certain occurrence frequency of combined foregrounds and their associated source foregrounds during training. Inspired by this, we introduce a novel composition style that binds the source and combined foregrounds in a definite triplet. In addition, we also find that different orders of foreground combination lead to different foreground patterns, which further inspires a quadruplet-based composition style. Results under controlled experiments on four matting baselines show that our composition styles outperform existing ones and invite consistent performance improvement on both composited and real-world datasets. Code is available at: https://github.com/coconuthust/composition_styles
