Let the Chart Spark: Embedding Semantic Context into Chart with Text-to-Image Generative Model

TL;DR

ChartSpark introduces a system that uses text-to-image generative models to embed semantic context into charts, enabling the creation of engaging pictorial visualizations that combine data accuracy with semantic richness.

Contribution

This work presents a novel, generic approach to embedding semantic context into charts using text-to-image generative models, along with an interactive interface for visualization creation and editing.

Findings

Demonstrated the usability of ChartSpark for generating pictorial visualizations.

Showed that the method effectively combines semantic context with data in charts.

Discussed the potential of generative models for visualization design.

Abstract

Pictorial visualization seamlessly integrates data and semantic context into visual representation, conveying complex information in a manner that is both engaging and informative. Extensive studies have been devoted to developing authoring tools to simplify the creation of pictorial visualizations. However, mainstream works mostly follow a retrieving-and-editing pipeline that heavily relies on retrieved visual elements from a dedicated corpus, which often compromise the data integrity. Text-guided generation methods are emerging, but may have limited applicability due to its predefined recognized entities. In this work, we propose ChartSpark, a novel system that embeds semantic context into chart based on text-to-image generative model. ChartSpark generates pictorial visualizations conditioned on both semantic context conveyed in textual inputs and data information embedded in plain charts. The method is generic for both foreground and background pictorial generation, satisfying the design practices identified from an empirical research into existing pictorial visualizations. We further develop an interactive visual interface that integrates a text analyzer, editing module, and evaluation module to enable users to generate, modify, and assess pictorial visualizations. We experimentally demonstrate the usability of our tool, and conclude with a discussion of the potential of using text-to-image generative model combined with interactive interface for visualization design.