[Paper] LottieGPT: Tokenizing Vector Animation for Autoregressive Generation
Paper Overview
Research area: cs.CV Authors: Junhao Chen, Kejun Gao, Yuehan Cui, Mingze Sun, Mingjin Chen, Shaohui Wang, Xiaoxiao Long, Fei Ma, Qi Tian, Ruqi Huang, Hao Zhao Published: 2026-04-13 arXiv: 2604.11792Summary
Despite rapid progress in video generation, existing models are incapable of producing vector animation, a dominant and highly expressive form of multimedia on the Internet. Vector animations offer resolution-independence, compactness, semantic structure, and editable parametric motion representations, yet current generative models operate exclusively in raster space and thus cannot synthesize them. This paper proposes the first framework for tokenizing and autoregressively generating vector animation. Adopting the widely deployed Lottie JSON animation standard, the authors design a custom Lottie Tokenizer that encodes hierarchical geometric primitives, transforms, and keyframe-based motion into compact, semantically aligned token sequences. They construct the LottieAnimation-660K dataset and fine-tune Qwen-VL to create LottieGPT, which can generate coherent, editable vector animations directly from natural-language or visual prompts.Original Abstract
Despite rapid progress in video generation, existing models are incapable of producing vector animation, a dominant and highly expressive form of multimedia on the Internet. Vector animations offer resolution-independence, compactness, semantic structure, and editable parametric motion representations, yet current generative models operate exclusively in raster space and thus cannot synthesize them.--- *Automatically collected on 2026-04-15*