Story3D-Agent: Exploring 3D Storytelling Visualization with Large Language Models

TL;DR

Story3D-Agent leverages large language models and procedural modeling to transform narratives into detailed, multi-character 3D visualizations, enabling dynamic and consistent storytelling beyond traditional 2D methods.

Contribution

It introduces a novel framework that combines LLMs with procedural modeling for comprehensive 3D storytelling visualization, surpassing existing 2D-focused approaches.

Findings

Effective transformation of narratives into 3D visualizations

Precise control over multi-character actions and decorations

Supports narrative extension with logical consistency

Abstract

Traditional visual storytelling is complex, requiring specialized knowledge and substantial resources, yet often constrained by human creativity and creation precision. While Large Language Models (LLMs) enhance visual storytelling, current approaches often limit themselves to 2D visuals or oversimplify stories through motion synthesis and behavioral simulation, failing to create comprehensive, multi-dimensional narratives. To this end, we present Story3D-Agent, a pioneering approach that leverages the capabilities of LLMs to transform provided narratives into 3D-rendered visualizations. By integrating procedural modeling, our approach enables precise control over multi-character actions and motions, as well as diverse decorative elements, ensuring the long-range and dynamic 3D representation. Furthermore, our method supports narrative extension through logical reasoning, ensuring that generated content remains consistent with existing conditions. We have thoroughly evaluated our Story3D-Agent to validate its effectiveness, offering a basic framework to advance 3D story representation.