AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens

Yiying Yang, Wei Cheng, Sijin Chen, Honghao Fu, Xianfang Zeng, Yujun Cai, Gang Yu, Xingjun Ma

CVPR 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Text-driven human motion generation · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add Lottie tokenizer instead of fine-tuning on raw JSON (ablation)Qwen2.5-VL · Text-to-Lottiesuccess rate: 13.4% -> 97.3%Improved
Add Lottie tokenizer instead of fine-tuning on raw JSON (ablation)Qwen2.5-VL · Text-to-LottieFVD: 459.39 -> 269.50Improved
Add Lottie tokenizer instead of fine-tuning on raw JSON (ablation)Qwen2.5-VL · Text-Image-to-LottieFVD: 476.23 -> 359.56Improved
Add Lottie tokenizer instead of fine-tuning on raw JSON (ablation)Qwen2.5-VL · Video-to-Lottiesuccess rate: 10.2% -> 90.7%Improved
Add Lottie tokenizer instead of fine-tuning on raw JSON (ablation)Qwen2.5-VL · Video-to-LottiePSNR: 17.23 -> 19.05Improved
Fine-tune pretrained Qwen2.5-VL (any form) vs zero-shot prompting (ablation)Qwen2.5-VL 3B · Text-to-Lottiesuccess rate: 0.0% -> 13.4% (raw JSON)Improved
Use OmniLottie instead of GPT-5Lottie generation · Text-to-Lottie (Real)FVD: 715.73 -> 202.14Improved
Use OmniLottie instead of RecraftText-to-Lottie · Real subsetobject alignment: 4.70 vs 4.44Mixed
Use OmniLottie instead of RecraftText-to-Lottie · Real subsetmotion alignment: 4.68 -> 5.94Improved
Use OmniLottie instead of optimization-based AniClipart/LivesketchText-Image-to-Lottie · Real subsetgeneration time (s): 1212.34 -> 88.57Improved
Move from Real to Synthetic subsetOmniLottie · Text-to-Lottiesuccess rate: 88.3% -> 82.1%Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy