ChartEditor: A Human-AI Paired Tool for Authoring Pictorial Charts

2025-01-13

AI Summary

Existing pictorial chart authoring tools (e.g., Tableau) suffer from cumbersome workflows and low efficiency, while AI-based generation methods lack pixel-level design control, compromising both aesthetic quality and geometric precision. To address this, we propose a human-AI collaborative, dual-modality editing framework—the first to integrate natural language understanding with direct manipulation via a hierarchical visual tree representation, unifying intent-driven specification and fine-grained control. Our approach decomposes charts into semantic visual components, models their relationships using a layered graph structure, parses multimodal user intents (text + interaction), and provides an interactive SVG-based editing interface. This enables intelligent generation of expressive, customizable pictorial charts from standard input charts. A user study demonstrates that our method significantly lowers the authoring barrier while improving both design accuracy and workflow efficiency.

Technology Category

• Humans and AI: Intelligent User Interfaces
• Computer Vision: Visual Reasoning & Symbolic Representations
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Pictorial charts are favored for their memorability and visual appeal, offering a more engaging alternative to basic charts. However, their creation can be complex and time-consuming due to the lack of native support in popular visualization tools like Tableau. While AI-generated content (AIGC) tools have lowered the barrier to creating pictorial charts, they often lack precise design control. To address this issue, we introduce ChartEditor, a human-AI paired tool that transforms basic charts into pictorial versions based on user intent. ChartEditor decomposes chart images into visual components and organizes them within a hierarchical tree. Based on this tree, users can express their intent in natural language, which is then translated into modifications to the hierarchy. In addition, users can directly interact with and modify specific chart components via an intuitive interface to achieve fine-grained design control. A user study demonstrates the effectiveness and usability of ChartEditor in simplifying the creation of pictorial charts.

Problem

• Complex Operation
• Time-consuming
• Lack of Precision Control

Innovation

• ChartEditor
• AI-assisted design
• Illustrated charts