Words as Art Materials: Generating Paintings with Sequential GANs

arxiv(2020)

引用 0|浏览1
暂无评分
摘要
Converting text descriptions into images using Generative Adversarial Networks has become a popular research area. Visually appealing images have been generated successfully in recent years. Inspired by these studies, we investigated the generation of artistic images on a large variance dataset. This dataset includes images with variations, for example, in shape, color, and content. These variations in images provide originality which is an important factor for artistic essence. One major characteristic of our work is that we used keywords as image descriptions, instead of sentences. As the network architecture, we proposed a sequential Generative Adversarial Network model. The first stage of this sequential model processes the word vectors and creates a base image whereas the next stages focus on creating high-resolution artistic-style images without working on word vectors. To deal with the unstable nature of GANs, we proposed a mixture of techniques like Wasserstein loss, spectral normalization, and minibatch discrimination. Ultimately, we were able to generate painting images, which have a variety of styles. We evaluated our results by using the Fr\'echet Inception Distance score and conducted a user study with 186 participants.
更多
查看译文
关键词
sequential gans,paintings,art materials,words
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要