论文标题
剪辑：使用可区分矢量图形的文本引导的图像操纵
CLIPVG: Text-Guided Image Manipulation Using Differentiable Vector Graphics
论文作者
论文摘要
最近在利用剪辑（对比度语言图像预训练）模型来进行文本引导的图像操纵方面取得了长足进展。但是，所有现有的作品都依靠其他生成模型来确保结果的质量，因为仅夹子不能为精细的像素级变化提供足够的指导信息。在本文中，我们介绍了使用可区分的向量图形的文本指导的图像操纵框架Clipvg，这也是第一个基于夹子的通用图像操作框架，不需要任何其他生成模型。我们证明，Clipvg不仅可以在语义正确性和合成质量中实现最新性能，而且还足够灵活，可以支持远远超出所有现有方法的能力的各种应用程序。
Considerable progress has recently been made in leveraging CLIP (Contrastive Language-Image Pre-Training) models for text-guided image manipulation. However, all existing works rely on additional generative models to ensure the quality of results, because CLIP alone cannot provide enough guidance information for fine-scale pixel-level changes. In this paper, we introduce CLIPVG, a text-guided image manipulation framework using differentiable vector graphics, which is also the first CLIP-based general image manipulation framework that does not require any additional generative models. We demonstrate that CLIPVG can not only achieve state-of-art performance in both semantic correctness and synthesis quality, but also is flexible enough to support various applications far beyond the capability of all existing methods.
