LiveSVG: Zero-Shot SVG Animation via Video Generation

2026-05-28

AI Summary

Existing SVG animation methods struggle to model complex non-rigid Bézier deformations and often rely on skeletal priors or produce noisy gradients. This work proposes a zero-shot SVG animation framework that first leverages a frozen image-to-video diffusion model to generate a target animation as a supervisory signal, then directly fits the original SVG to this video via differentiable rendering. The key innovations include a skeleton-free, two-level motion representation—combining group-level homography transformations with path-level Bézier control point offsets—and a sphere-filling recoloring strategy, which together effectively address challenges in local deformation modeling and color ambiguity. Evaluated on AniClipart and the newly introduced ChallengeSVG benchmark, the method significantly outperforms existing approaches, producing semantically aligned, fully editable, high-quality vector animations.

Abstract

We introduce LiveSVG, a zero-shot approach for generating Scalable Vector Graphics (SVG) animations using video diffusion models. Current SVG animation methods struggle with complex motions: LLM-based code synthesis fails to express fine, non-rigid Bézier deformations, while Score Distillation Sampling (SDS) provides noisy gradients and often requires category-specific priors like skeletons. In contrast, LiveSVG fits vector geometry directly to an explicitly generated target video. Given an input SVG image and a motion prompt, we generate a previewable target video using a frozen image-to-video model, then fit the original SVG to this video via differentiable rendering. Our fitting stage is skeleton-free, utilizing a dual-level motion representation that combines per-group homographies for coarse articulation with per-path Bézier control-point offsets for local deformations. To resolve color-induced correspondence ambiguities during pixel-wise fitting, we introduce a novel sphere-packing recolorization strategy. We also present ChallengeSVG, a benchmark of complex, multi-object scenes that exposes the limitations of prior work. Evaluations demonstrate that LiveSVG significantly outperforms existing methods on both AniClipart and ChallengeSVG, establishing direct reference-video fitting as a practical, robust route to prompt-aligned and fully editable vector animation.

Problem

• SVG animation
• complex motion
• non-rigid deformation
• vector graphics
• animation generation

Innovation

• zero-shot animation
• SVG animation
• video diffusion models
• differentiable rendering
• sphere-packing recolorization