Matan 
Cornell Tech
Hebrew University of Jerusalem
Google
IBM Research AI
SIGGRAPH Asia, 2026
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.
Matan Levy
I am a Postdoctoral Researcher at
Cornell Tech,
working with
Prof. Hadar Averbuch-Elor and Prof. Or Litany.
I completed my Ph.D. in Computer Science at the
School of Computer Science and Engineering,
Hebrew University of Jerusalem,
advised by
Prof. Dani Lischinski.
Previously, I was a Student Researcher at Google, working on Generative AI for Computer Vision applications, and a Research Intern at IBM Research AI.
My research interests include Computer Vision, Natural Language Processing, and tasks that combine both domains. I also stay actively involved in the research community as a reviewer for NeurIPS, SIGGRAPH, ICLR, Pattern Recognition (PR), ICML, ICCV, AAAI, and CVPR, and I am always glad to contribute.
