In this paper, we tackle a challenging domain conversion task between photo and icon images. Although icons often originate from real object images (i.e., photographs), severe abstractions and simplifications are applied to generate icon images by professional graphic designers. Moreover, there is no one-to-one correspondence between the two domains, for this reason we cannot use it as the ground-truth for learning a direct conversion function. Since generative adversarial networks (GAN) can undertake the problem of domain conversion without any correspondence, we test CycleGAN and UNIT to generate icons from objects segmented from photo images. Our experiments with several image datasets prove that CycleGAN learns sufficient abstraction and simplification ability to generate icon-like images.

中文翻译：

---

Iconify：将照片转换为图标

在本文中，我们解决了照片和图标图像之间具有挑战性的域转换任务。尽管图标通常源自真实物体图像（即照片），但专业图形设计师应用严格的抽象和简化来生成图标图像。此外，两个域之间没有一一对应的关系，因此我们不能将其用作学习直接转换函数的基本事实。由于生成对抗网络（GAN）可以在没有任何对应关系的情况下承担域转换问题，我们测试 CycleGAN 和 UNIT 以从照片图像分割的对象生成图标。我们对多个图像数据集的实验证明 CycleGAN 学习了足够的抽象和简化能力来生成类似图标的图像。