AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

Vector Prism: Animating Vector Graphics by Stratifying Semantic Structure

Jooyeol Yun, Jaegul Choo

CVPR 2026 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
restructure SVG into semantic groups via Dawid-Skene weighted voting before animating with an LLMVector Prism (GPT-5 animation) · SVG animation, 114 pairsGPT-T2V: 40.92 (GPT-5 pipeline) -> 76.14Improved
use reliability-weighted Bayes decision rule instead of majority voting over rendering views (ablation)Vector Prism semantic labeling · Semantic grouping, DBIDavies-Bouldin index: 12.6 -> 0.82Improved
aggregate multi-view VLM labels rather than keep the original rendering-oriented SVG groupings (ablation)SVG semantic grouping · Semantic grouping, DBIDavies-Bouldin index: 33.8 -> 12.6 (majority voting)Improved
generate vector CSS animations instead of raster videoVector Prism vs Sora 2 · Encoding efficiencyfile size: 54.8x compression vs Sora 2Improved
use vector-based animation instead of video generation models for instruction followingVector Prism vs Sora 2 / Wan 2.2 · User studypreference: 63.3% vs Sora 2; 76.5% vs Wan 2.2Improved
compare video models against Vector Prism on perceptual qualityWan 2.2 and Sora 2 · DOVERDOVER: Wan 2.2 3.72, Sora 2 4.19 vs Ours 4.97Hurt
limit motion to raise perceptual qualityGPT-5 pipeline without semantic structure · DOVER vs GPT-T2VDOVER / GPT-T2V: DOVER 4.92 but GPT-T2V 40.92Mixed
treat SVG primitives as atomic units without subdividingVector Prism · Failure caseinstruction followingHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy