论文标题
$ f $，$ b $，alpha matting
$F$, $B$, Alpha Matting
论文作者
论文摘要
切出一个对象并估算其不透明度掩码，称为图像垫，是许多图像编辑应用程序中的关键任务。深度学习方法通过调整分割网络的编码器架构来取得重大进展。但是，大多数现有网络仅预测Alpha Matte和后处理方法，然后必须使用后处理方法来恢复透明区域中的原始前景和背景颜色。最近，两种方法通过还估计前景颜色，但以显着的计算和内存成本来显示出改进的结果。 在本文中，我们建议对Alpha Matting网络进行低成本修改，以预测前景和背景颜色。我们研究训练制度的变化，并探讨了联合预测的广泛现有和新颖的损失功能。 我们的方法在Adobe组成-1K数据集上实现了用于Alpha Matte和复合色彩质量的最先进的性能。这也是Alphamatting.com在线评估的当前最佳性能方法。
Cutting out an object and estimating its opacity mask, known as image matting, is a key task in many image editing applications. Deep learning approaches have made significant progress by adapting the encoder-decoder architecture of segmentation networks. However, most of the existing networks only predict the alpha matte and post-processing methods must then be used to recover the original foreground and background colours in the transparent regions. Recently, two methods have shown improved results by also estimating the foreground colours, but at a significant computational and memory cost. In this paper, we propose a low-cost modification to alpha matting networks to also predict the foreground and background colours. We study variations of the training regime and explore a wide range of existing and novel loss functions for the joint prediction. Our method achieves the state of the art performance on the Adobe Composition-1k dataset for alpha matte and composite colour quality. It is also the current best performing method on the alphamatting.com online evaluation.
