MapStory: Prototyping Editable Map Animations with LLM Agents

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Gunturu, Aditya, Pearman, Ben, Ihara, Keiichi, Faraji, Morteza, Wang, Bryan, Kazi, Rubaiat Habib, Suzuki, Ryo
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908487379845120
author Gunturu, Aditya
Pearman, Ben
Ihara, Keiichi
Faraji, Morteza
Wang, Bryan
Kazi, Rubaiat Habib
Suzuki, Ryo
author_facet Gunturu, Aditya
Pearman, Ben
Ihara, Keiichi
Faraji, Morteza
Wang, Bryan
Kazi, Rubaiat Habib
Suzuki, Ryo
contents We introduce MapStory, an LLM-powered animation prototyping tool that generates editable map animation sequences directly from natural language text by leveraging a dual-agent LLM architecture. Given a user written script, MapStory automatically produces a scene breakdown, which decomposes the text into key map animation primitives such as camera movements, visual highlights, and animated elements. Our system includes a researcher agent that accurately queries geospatial information by leveraging an LLM with web search, enabling automatic extraction of relevant regions, paths, and coordinates while allowing users to edit and query for changes or additional information to refine the results. Additionally, users can fine-tune parameters of these primitive blocks through an interactive timeline editor. We detail the system's design and architecture, informed by formative interviews with professional animators and by an analysis of 200 existing map animation videos. Our evaluation, which includes expert interviews (N=5) and a usability study (N=12), demonstrates that MapStory enables users to create map animations with ease, facilitates faster iteration, encourages creative exploration, and lowers barriers to creating map-centric stories.
format Preprint
id arxiv_https___arxiv_org_abs_2505_21966
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MapStory: Prototyping Editable Map Animations with LLM Agents
Gunturu, Aditya
Pearman, Ben
Ihara, Keiichi
Faraji, Morteza
Wang, Bryan
Kazi, Rubaiat Habib
Suzuki, Ryo
Human-Computer Interaction
Artificial Intelligence
Computation and Language
Multimedia
H.5.2, H.5.1
We introduce MapStory, an LLM-powered animation prototyping tool that generates editable map animation sequences directly from natural language text by leveraging a dual-agent LLM architecture. Given a user written script, MapStory automatically produces a scene breakdown, which decomposes the text into key map animation primitives such as camera movements, visual highlights, and animated elements. Our system includes a researcher agent that accurately queries geospatial information by leveraging an LLM with web search, enabling automatic extraction of relevant regions, paths, and coordinates while allowing users to edit and query for changes or additional information to refine the results. Additionally, users can fine-tune parameters of these primitive blocks through an interactive timeline editor. We detail the system's design and architecture, informed by formative interviews with professional animators and by an analysis of 200 existing map animation videos. Our evaluation, which includes expert interviews (N=5) and a usability study (N=12), demonstrates that MapStory enables users to create map animations with ease, facilitates faster iteration, encourages creative exploration, and lowers barriers to creating map-centric stories.
title MapStory: Prototyping Editable Map Animations with LLM Agents
topic Human-Computer Interaction
Artificial Intelligence
Computation and Language
Multimedia
H.5.2, H.5.1
url https://arxiv.org/abs/2505.21966