Abstract
Sketching is more fundamental to human cognition than speech. Deep Neural Networks (DNNs) have achieved the state-of-the-art in speech-related tasks but have not made significant development in generating stroke-based sketches a.k.a sketches in vector format. Though there are Variational Auto Encoders (VAEs) for generating sketches in vector format, there is no Generative Adversarial Network (GAN) architecture for the same. In this paper, we propose a standalone GAN architecture SkeGAN and a VAE-GAN architecture VASkeGAN, for sketch generation in vector format. SkeGAN is a stochastic policy in Reinforcement Learning (RL), capable of generating both multidimensional continuous and discrete outputs. VASkeGAN hybridizes a VAE and a GAN, in order to couple the efficient representation of data by VAE with the powerful generating capabilities of a GAN, to produce visually appealing sketches. We also propose a new metric called the Ske-score which quantifies the quality of vector sketches. We have validated that SkeGAN and VASkeGAN generate visually appealing sketches by using Human Turing Test and Ske-score.
Abstract (translated)
素描比言语对人类认知更为重要。深度神经网络(DNN)在语言相关任务方面已经达到了最先进的水平,但在以矢量格式生成基于中风的草图A.K.A方面还没有取得重大进展。虽然有变分自动编码器(vaes)生成矢量格式的草图,但没有生成对抗网络(gan)架构。在本文中,我们提出了一个独立的gan架构skegan和一个vae-gan架构vaskegan,用于矢量格式的草图生成。skegan是强化学习(rl)中的一种随机策略,能够产生多维连续和离散的输出。Vaskegan混合了一个VAE和一个GAN,以便将VAE对数据的有效表示与一个GAN强大的生成能力结合起来,以生成具有视觉吸引力的草图。我们还提出了一个新的指标,称为SKE分数,量化矢量草图的质量。我们已经验证了skegan和vaskegan通过使用人类图灵测试和ske评分生成视觉上吸引人的草图。
URL
https://arxiv.org/abs/1904.03620