ArtGAN: Artwork Synthesis with Conditional Categorical GANs
2017 IEEE International Conference on Image Processing (ICIP)(2017)
摘要
This paper proposes an extension to the Generative Adversarial Networks (GANs), namely as ARTGAN to synthetically generate more challenging and complex images such as artwork that have abstract characteristics. This is in contrast to most of the current solutions that focused on generating natural images such as room interiors, birds, flowers and faces. The key innovation of our work is to allow back-propagation of the loss function w.r.t. the labels (randomly assigned to each generated images) to the generator from the discriminator. With the feedback from the label information, the generator is able to learn faster and achieve better generated image quality. Empirically, we show that the proposed ARTGAN is capable to create realistic artwork, as well as generate compelling real world images that globally look natural with clear shape on CIFAR-10.
更多查看译文
关键词
image synthesis,generative adversarial networks,deep learning
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络