DataMagic: Transforming Tabular Data into Data Insight Video

2026-06-18

AI Summary

This work addresses the challenge that existing tools struggle to automatically generate insight videos from raw tabular data that simultaneously exhibit strong narrative structure, engaging animation, and high data fidelity. The authors propose an end-to-end interactive system that transforms tabular data and natural language queries into narrated videos featuring dynamic visualizations, spoken explanations, and synchronized animations. Key innovations include a declarative specification language, DVSpec, to ensure data faithfulness; a generate-and-orchestrate multi-agent architecture to manage the combinatorial explosion of the design space; and a structured provenance mechanism enabling exploratory, interactive question answering. Evaluation on 109 real-world examples demonstrates that the system efficiently produces high-quality, interactive, and data-accurate narrative videos.

Abstract

Data videos integrate dynamic charts, voice narration, and synchronized animations to communicate data insights as temporal narratives, making them an effective medium for improving data consumption efficiency in the data management lifecycle. However, producing high-quality data videos requires expertise spanning data analysis, narrative design, and video production. Existing approaches fall short: static visualization tools (e.g., BI dashboards) lack narrative logic and animation; authoring tools require users to pre-prepare visualizations rather than working from raw data; pixel-level video generation models cannot guarantee data fidelity or provenance. We demonstrate DataMagic, an end-to-end interactive system that transforms raw tabular data and natural language queries into narrative data-insight videos. To ensure data fidelity, DataMagic introduces the declarative specification DVSpec, which binds visual and animation elements to underlying data fields through data-driven semantic references. To address the combinatorial explosion of the design space, DataMagic adopts a Generate-then-Orchestrate multi-agent architecture that generates candidate scenes in parallel and then optimizes narrative coherence through global orchestration. Leveraging DVSpec's decoupling of logic and rendering, the system further supports three interaction modes and structured provenance-based data Q&A, transforming one-way videos into explorable interactive data interfaces. Evaluation on 109 real-world samples validates the effectiveness of the DataMagic. Homepage: https://datamagic-home.github.io/

Problem

• data video
• tabular data
• data fidelity
• narrative visualization
• automated video generation

Innovation

• DVSpec
• data video
• multi-agent architecture
• data fidelity
• interactive data narrative