ReVis: Towards Reusable Image-Based Visualizations with MLLMs

2026-04-17

AI Summary

This work addresses the limited reusability and adaptability of bitmap visualizations shared online, which existing approaches struggle to overcome due to reliance on structured formats, narrow chart-type coverage, and insufficient customization capabilities. The authors propose a human-in-the-loop framework that leverages multimodal large language models (MLLMs) to parse bitmap visualizations into a domain-specific language (DSL) capable of expressing complex chart structures. This DSL enables end-to-end reconstruction of both visualization layout and data mappings, supporting interactive data updates and customizable visual encodings. The expressiveness of the DSL is validated on a benchmark comprising 40 diverse chart styles, with quantitative evaluations demonstrating high-fidelity reproductions. A user study involving 16 practitioners further confirms the system’s practical utility and effectiveness in real-world scenarios.

Technology Category

• Data Mining & Knowledge Management: Data Visualization & Summarization
• Computer Vision: Visual Reasoning & Symbolic Representations
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Many expressive visualizations are shared online only as bitmap images, making them difficult to redesign or adapt to new data. Reusing such image-based visualizations requires substantial expertise and is often time-consuming, even for experienced visualization practitioners. Existing work on reproducing visualizations often relies on structured SVG or specifications, supports limited visualization types, and offers limited flexibility for customization. To address these challenges, we present ReVis, a human-AI collaboration approach that enables flexible reuse of image-based visualizations. First, a generic Domain-Specific language (DSL) is proposed to model complex visualizations and support both visualization decomposition and reproduction. Then, ReVis employs an MLLM-based pipeline to parse an image-based visualization into the DSL, delineating its core visual structures and data-to-encoding mappings, and further reproduces the visualization from the DSL. Finally, ReVis includes an interactive interface to allow users to upload visualization images, inspect reproduced results, update the underlying data, and customize visual encodings. A gallery of 40 visualizations demonstrates the expressiveness of the DSL, and a quantitative study evaluates the reproduction quality of ReVis on these examples. Two usage scenarios and user interviews with 16 visualization practitioners demonstrate the effectiveness of ReVis.

Problem

• image-based visualizations
• visualization reuse
• bitmap images
• data adaptation
• visualization reproduction

Innovation

• MLLM
• Domain-Specific Language
• Visualization Reproduction
• Image-Based Visualization
• Human-AI Collaboration