Vector Prism: Animating Vector Graphics by Stratifying Semantic Structure

TL;DR

This paper presents Vector Prism, a framework that recovers semantic structure in SVGs to enable more coherent and reliable animations by vision-language models, addressing current fragmentation issues.

Contribution

It introduces a novel semantic aggregation method that reorganizes SVGs into meaningful groups, significantly improving animation coherence in VLMs.

Findings

Substantial improvements over existing methods in SVG animation quality

Semantic recovery enhances interpretability of VLM interactions with vector graphics

Stable inference of semantics from noisy predictions is achieved

Abstract

Scalable Vector Graphics (SVG) are central to modern web design, and the demand to animate them continues to grow as web environments become increasingly dynamic. Yet automating the animation of vector graphics remains challenging for vision-language models (VLMs) despite recent progress in code generation and motion planning. VLMs routinely mis-handle SVGs, since visually coherent parts are often fragmented into low-level shapes that offer little guidance of which elements should move together. In this paper, we introduce a framework that recovers the semantic structure required for reliable SVG animation and reveals the missing layer that current VLM systems overlook. This is achieved through a statistical aggregation of multiple weak part predictions, allowing the system to stably infer semantics from noisy predictions. By reorganizing SVGs into semantic groups, our approach enables VLMs to produce animations with far greater coherence. Our experiments demonstrate substantial gains over existing approaches, suggesting that semantic recovery is the key step that unlocks robust SVG animation and supports more interpretable interactions between VLMs and vector graphics.