论文标题
单个增强训练样本中的图像形状操纵
Image Shape Manipulation from a Single Augmented Training Sample
论文作者
论文摘要
在本文中，我们提出了DeepSim，这是一种基于单个图像的条件图像操纵的生成模型。我们发现，广泛的增强是实现单个图像训练的关键，并结合了薄板拼接（TPS）作为有效增强的关键。我们的网络学会在图像本身的原始表示之间映射。原始表示的选择会影响操纵的易度性和表现性，并且可以是自动的（例如边缘），手册（例如分割）或杂种，例如分段的边缘。在操作时，我们的生成器可以通过修改原始输入表示并通过网络映射来进行复杂的图像更改。我们的方法显示出在图像操纵任务上实现出色的性能。
In this paper, we present DeepSIM, a generative model for conditional image manipulation based on a single image. We find that extensive augmentation is key for enabling single image training, and incorporate the use of thin-plate-spline (TPS) as an effective augmentation. Our network learns to map between a primitive representation of the image to the image itself. The choice of a primitive representation has an impact on the ease and expressiveness of the manipulations and can be automatic (e.g. edges), manual (e.g. segmentation) or hybrid such as edges on top of segmentations. At manipulation time, our generator allows for making complex image changes by modifying the primitive input representation and mapping it through the network. Our method is shown to achieve remarkable performance on image manipulation tasks.
