论文标题
语言图像图表预处理表示零拍的素描至图像合成中的样式符合性删除
Style-Content Disentanglement in Language-Image Pretraining Representations for Zero-Shot Sketch-to-Image Synthesis
论文作者
论文摘要
在这项工作中，我们提出并验证一个框架，以利用语言图像预处理表示形式来训练零拍的素描至图像合成。我们表明，可以利用删除的内容和样式表示形式来指导图像发生器将它们用作素描到图像生成器，而无需（重新）培训任何参数。我们解开样式和内容的方法需要一种简单的方法，该方法由基本算术组成，假设在输入草图表示中信息的组成性。我们的结果表明，这种方法与最先进的实例级开放域素描到图像模型具有竞争力，而仅取决于预定的现成模型和一小部分数据。
In this work, we propose and validate a framework to leverage language-image pretraining representations for training-free zero-shot sketch-to-image synthesis. We show that disentangled content and style representations can be utilized to guide image generators to employ them as sketch-to-image generators without (re-)training any parameters. Our approach for disentangling style and content entails a simple method consisting of elementary arithmetic assuming compositionality of information in representations of input sketches. Our results demonstrate that this approach is competitive with state-of-the-art instance-level open-domain sketch-to-image models, while only depending on pretrained off-the-shelf models and a fraction of the data.
