论文标题
图像产生的语义金字塔
Semantic Pyramid for Image Generation
论文作者
论文摘要
我们提出了一种基于GAN的新型模型，该模型利用了通过预训练的分类模型学到的深度特征的空间。受经典图像金字塔表示的启发，我们将模型构建为语义一代金字塔，这是一个层次结构框架，它利用了封装在如此深的特征中的语义信息的连续性；从精细功能中包含的低级别信息到高级别的范围，更深的功能中包含的语义信息。更具体地说，给定从参考图像提取的一组功能，我们的模型生成了各种图像样本，每个图像样本都在分类模型的每个语义级别都具有匹配的特征。我们证明，我们的模型会导致多功能且灵活的框架，该框架可用于各种经典和新颖的图像生成任务。其中包括：生成与参考图像具有可控语义相似性的图像，以及不同的操纵任务，例如语义控制的授课和合成；所有这些都以相同的模型实现，没有进一步的培训。
We present a novel GAN-based model that utilizes the space of deep features learned by a pre-trained classification model. Inspired by classical image pyramid representations, we construct our model as a Semantic Generation Pyramid -- a hierarchical framework which leverages the continuum of semantic information encapsulated in such deep features; this ranges from low level information contained in fine features to high level, semantic information contained in deeper features. More specifically, given a set of features extracted from a reference image, our model generates diverse image samples, each with matching features at each semantic level of the classification model. We demonstrate that our model results in a versatile and flexible framework that can be used in various classic and novel image generation tasks. These include: generating images with a controllable extent of semantic similarity to a reference image, and different manipulation tasks such as semantically-controlled inpainting and compositing; all achieved with the same model, with no further training.
