论文标题
创意素描一代
Creative Sketch Generation
论文作者
论文摘要
素描或涂鸦是人们从事的一种流行的创意活动。但是，自动素描理解或一代中的大多数现有作品都集中在相当平凡的草图上。在这项工作中，我们介绍了两个创意草图的数据集 - 创意鸟类和创意生物，其中包含10k草图以及部分注释。我们提出了Doodlergan（基于部分的生成对抗网络（GAN）），以生成新型零件外观的看不见的组成。定量评估以及人类研究表明，我们方法产生的草图比现有方法更具创造力和更高的质量。实际上，在创意鸟类中，受试者更喜欢杜德勒根（Doodlergan）产生的草图，而不是人类吸引的素描！可以在https://github.com/facebookresearch/doodlergan上找到我们的代码，可以在http://doodlergan.cloudcv.org上找到演示。
Sketching or doodling is a popular creative activity that people engage in. However, most existing work in automatic sketch understanding or generation has focused on sketches that are quite mundane. In this work, we introduce two datasets of creative sketches -- Creative Birds and Creative Creatures -- containing 10k sketches each along with part annotations. We propose DoodlerGAN -- a part-based Generative Adversarial Network (GAN) -- to generate unseen compositions of novel part appearances. Quantitative evaluations as well as human studies demonstrate that sketches generated by our approach are more creative and of higher quality than existing approaches. In fact, in Creative Birds, subjects prefer sketches generated by DoodlerGAN over those drawn by humans! Our code can be found at https://github.com/facebookresearch/DoodlerGAN and a demo can be found at http://doodlergan.cloudcv.org.
