VAnim: Rendering-Aware Sparse State Modeling for Structure-Preserving Vector Animation

TL;DR

VAnim is a novel LLM-based framework for open-domain SVG animation that models sparse state updates to preserve structure and enable precise control, significantly improving semantic alignment and validity.

Contribution

It introduces a new paradigm of Sparse State Updates for SVG animation, along with a control mechanism and reinforcement learning approach, and provides the SVGAnim-134k benchmark.

Findings

VAnim compresses sequence length by over 9.8x.

Outperforms baselines in semantic alignment and structural validity.

Achieves high-fidelity visual feedback through rendering-aware reinforcement learning.

Abstract

Scalable Vector Graphics (SVG) animation generation is pivotal for professional design due to their structural editability and resolution independence. However, this task remains challenging as it requires bridging discrete code representations with continuous visual dynamics. Existing optimization-based methods often destroy topological consistency, while general-purpose LLMs rely on rigid CSS/SMIL transformations, failing to model geometry-level non-rigid deformations. To address these limitations, we present VAnim, the first LLM-based framework for open-domain text-to-SVG animation. We reconceptualize animation not as sequence generation, but as Sparse State Updates (SSU) on a persistent SVG DOM tree. This paradigm compresses sequence length by over 9.8x while preserving the SVG DOM structure and non-participating elements by construction. To enable precise control, we propose an Identification-First Motion Planning mechanism that grounds textual instructions in explicit visual entities. Furthermore, to overcome the non-differentiable nature of SVG rendering, we employ Rendering-Aware Reinforcement Learning via Group Relative Policy Optimization (GRPO). By leveraging a hybrid reward from a state-of-the-art video perception encoder, we align discrete code updates with high-fidelity visual feedback. We also introduce SVGAnim-134k, the first benchmark for vector animation. Extensive experiments demonstrate that VAnim significantly outperforms state-of-the-art baselines in semantic alignment and structural validity, with additional appendix metrics further validating motion quality and identity preservation.