DataWink: Reusing and Adapting SVG-based Visualization Examples with Large Multimodal Models
read the original abstract
Creating aesthetically pleasing data visualizations remains challenging for users without design expertise or familiarity with visualization tools. To address this gap, we present DataWink, a system that enables users to create custom visualizations by adapting high-quality examples. Our approach combines large multimodal models (LMMs) to extract data encoding from existing SVG-based visualization examples, featuring an intermediate representation of visualizations that bridges primitive SVG and visualization programs. Users may express adaptation goals to a conversational agent and control the visual appearance through widgets generated on demand. With an interactive interface, users can modify both data mappings and visual design elements while maintaining the original visualization's aesthetic quality. To evaluate DataWink, we conduct a user study (N=12) with replication and free-form exploration tasks. As a result, DataWink is recognized for its learnability and effectiveness in personalized authoring tasks. Our results demonstrate the potential of example-driven approaches for democratizing visualization creation.
This paper has not been read by Pith yet.
Forward citations
Cited by 4 Pith papers
-
ReVis: Towards Reusable Image-Based Visualizations with MLLMs
ReVis parses image-based visualizations into a reusable DSL via an MLLM pipeline and supports reproduction, data updates, and customization through an interactive interface.
-
From Static to Interactive: Authoring Interactive Visualizations via Natural Language
Athanor converts static visualizations to interactive versions via MLLMs, a multi-agent analyzer, and an abstraction transformer, allowing natural language authoring of interactions.
-
Elemental Alchemist: A Generative Interface for Semantic Control of Particle Systems Across Dynamic Levels of Abstraction
Elemental Alchemist generates contextual tools and abstracts particle-system parameters into semantic mid-level attributes and high-level conceptual controls, with a user study indicating it helps practitioners transl...
-
DataSway: Vivifying Metaphoric Visualization with Animation Clip Generation and Coordination
DataSway supports creation of semantically aligned animations for metaphoric data visualizations by generating clips via VLMs and coordinating timelines based on entity order, attributes, layout, or randomness.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.