Automatic Image Synthesis from Keywords Using Scene Context
Automatic Image Synthesis from Keywords Using Scene Context
复制标题
DOI：
10.1145/2647868.2655009
复制
发表时间：
2014-11
期刊：
影响因子：
--
通讯作者：
Sho Inaba;Asako Kanezaki;T. Harada
中科院分区：
文献类型：
--
作者：
Sho Inaba;Asako Kanezaki;T. Harada
文字是表达一个人思想的最简单的方式之一，而图像是最具影响力的方式之一。因此，如果一个系统可以从文本合成图像，而无需用户直接操作，那么新的图像合成应用程序将向没有艺术技能的用户开放。在这样一个系统中，哪些对象要合成将在文本中声明。然而，关于对象的位置关系和尺度的信息提供得不多，并且必须使用常识来估计。如本文所述，我们开发了一个系统，可以自动合成对象的图像，给定的背景图像和目标合成对象的类名。利用作为背景图像和关键字的输入，自动搜索用于合成对象的图像。虽然之前开发的一些系统可以从草图和绘画合成图像，但这是第一个可以估计物体的位置，比例和外观并自动将其合成为图像而无需直接用户输入的系统。我们提出了一个场景上下文，它指示合成对象的位置，规模和外观。本文的贡献是两方面的：（1）场景上下文提取方法的自动图像合成和（2）使用场景上下文的自动图像合成的应用。
Text is one of the simplest way to express one's idea, and an image is one of the most impactive way to do so. Therefore, if a system can synthesize an image from text without direct user manipulation, novel image synthesis applications will be opened to users without artistic skills. In such a system, which objects to synthesize will be declared in texts. However, information about positional relations and scale of objects is not much provided and must be estimated using common sense. As described in this paper, we develop a system that can automatically synthesize objects to an image, given the background image and class name of the target synthesizing object. With the inputs as the background image and keywords, images for synthesizing objects are searched automatically. Although some previously developed systems that can synthesize an image from sketches and paintings, this is the first system that can estimate the position, scale, and appearance of objects and automatically synthesize them to images without direct user input. We propose a scene context, which indicates the position, scale, and appearance of synthesizing objects. The contribution of this paper is twofold: (1) the scene context extraction method for automatic image synthesis and (2) application of automatic image synthesis using the scene context.