A Novel Approach to Artistic Textual Visualization via GAN

TL;DR

This paper introduces GAN-ATV, a novel generative model that creates artistic paintings from poems by analyzing semantic content and synthesizing visual information, advancing artistic textual visualization.

Contribution

The paper presents a new GAN-based framework for artistic textual visualization, including a semantic analysis method and a cross-modal dataset for training and evaluation.

Findings

GAN-ATV effectively generates paintings from poems

The cross-modal dataset Cross-Art supports model training

Experimental results demonstrate high semantic consistency

Abstract

While the visualization of statistical data tends to a mature technology, the visualization of textual data is still in its infancy, especially for the artistic text. Due to the fact that visualization of artistic text is valuable and attractive in both art and information science, we attempt to realize this tentative idea in this article. We propose the Generative Adversarial Network based Artistic Textual Visualization (GAN-ATV) which can create paintings after analyzing the semantic content of existing poems. Our GAN-ATV consists of two main sections: natural language analysis section and visual information synthesis section. In natural language analysis section, we use Bag-of-Word (BoW) feature descriptors and a two-layer network to mine and analyze the high-level semantic information from poems. In visual information synthesis section, we design a cross-modal semantic understanding module and integrate it with Generative Adversarial Network (GAN) to create paintings, whose content are corresponding to the original poems. Moreover, in order to train our GAN-ATV and verify its performance, we establish a cross-modal artistic dataset named "Cross-Art". In the Cross-Art dataset, there are six topics and each topic has their corresponding paintings and poems. The experimental results on Cross-Art dataset are shown in this article.