Xiao Shishi, Huang Suizi, Lin Yue, Ye Yilin, Zeng Wei
IEEE Trans Vis Comput Graph. 2024 Jan;30(1):284-294. doi: 10.1109/TVCG.2023.3326913. Epub 2023 Dec 25.
Pictorial visualization seamlessly integrates data and semantic context into visual representation, conveying complex information in an engaging and informative manner. Extensive studies have been devoted to developing authoring tools to simplify the creation of pictorial visualizations. However, mainstream works follow a retrieving-and-editing pipeline that heavily relies on retrieved visual elements from a dedicated corpus, which often compromise data integrity. Text-guided generation methods are emerging, but may have limited applicability due to their predefined entities. In this work, we propose ChartSpark, a novel system that embeds semantic context into chart based on text-to-image generative models. 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 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 models combined with an interactive interface for visualization design.
图形可视化将数据和语义上下文无缝集成到视觉表示中，以引人入胜且信息丰富的方式传达复杂信息。大量研究致力于开发创作工具，以简化图形可视化的创建。然而，主流作品遵循一种检索和编辑流程，严重依赖从专用语料库中检索的视觉元素，这往往会损害数据完整性。文本引导的生成方法正在兴起，但由于其预定义的实体，可能适用性有限。在这项工作中，我们提出了ChartSpark，这是一种基于文本到图像生成模型将语义上下文嵌入图表的新颖系统。ChartSpark根据文本输入中传达的语义上下文和普通图表中嵌入的数据信息生成图形可视化。该方法对于前景和背景图形生成都是通用的，满足从对现有图形可视化的实证研究中确定的设计实践。我们进一步开发了一个交互式视觉界面，该界面集成了文本分析器、编辑模块和评估模块，以使用户能够生成、修改和评估图形可视化。我们通过实验证明了我们工具的可用性，并最后讨论了将文本到图像生成模型与交互式界面结合用于可视化设计的潜力。
