LiveSVG: Zero-Shot SVG Animation via Video Generation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Levy, Matan, Margolin, Ran, Cavia, Bar, Samuel, Dvir, Pritch, Yael, Peleg, Shmuel, Acha, Alex Rav, Shamir, Ariel, Lischinski, Dani
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911728585932800
author Levy, Matan
Margolin, Ran
Cavia, Bar
Samuel, Dvir
Pritch, Yael
Peleg, Shmuel
Acha, Alex Rav
Shamir, Ariel
Lischinski, Dani
author_facet Levy, Matan
Margolin, Ran
Cavia, Bar
Samuel, Dvir
Pritch, Yael
Peleg, Shmuel
Acha, Alex Rav
Shamir, Ariel
Lischinski, Dani
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_30174
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle LiveSVG: Zero-Shot SVG Animation via Video Generation
Levy, Matan
Margolin, Ran
Cavia, Bar
Samuel, Dvir
Pritch, Yael
Peleg, Shmuel
Acha, Alex Rav
Shamir, Ariel
Lischinski, Dani
Computer Vision and Pattern Recognition
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.
title LiveSVG: Zero-Shot SVG Animation via Video Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.30174