MoVer: Motion Verification for Motion Graphics Animations
Jiaju Ma, Maneesh Agrawala

TL;DR
MoVer introduces a logic-based verification system for motion graphics animations, enabling iterative refinement of animations generated from text prompts using an LLM pipeline.
Contribution
We develop MoVer, a first-order logic-based DSL for verifying spatio-temporal properties of motion graphics, integrated into an LLM-driven synthesis and correction pipeline.
Findings
Correct animations generated for 58.8% of prompts without iteration
Iterative correction improves accuracy to 93.6%
Built a synthetic dataset of 5600 prompt-annotation pairs
Abstract
While large vision-language models can generate motion graphics animations from text prompts, they regularly fail to include all spatio-temporal properties described in the prompt. We introduce MoVer, a motion verification DSL based on first-order logic that can check spatio-temporal properties of a motion graphics animation. We identify a general set of such properties that people commonly use to describe animations (e.g., the direction and timing of motions, the relative positioning of objects, etc.). We implement these properties as predicates in MoVer and provide an execution engine that can apply a MoVer program to any input SVG-based motion graphics animation. We then demonstrate how MoVer can be used in an LLM-based synthesis and verification pipeline for iteratively refining motion graphics animations. Given a text prompt, our pipeline synthesizes a motion graphics animation and…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
MethodsSparse Evolutionary Training
