开源百万级高质量动作数据集，提升文本生成动作的泛化能力
OpenT2M: No-frill Motion Generation with Open-source,Large-scale, High-quality Data
- 构建百万级动作数据集，每帧做物理合理性验证
- 新模型2D-PRQ在零样本下仍保持高精度动作重建
- 适合动画、机器人领域研究者快速复现与开发
文本到动作（T2M）生成旨在从文本描述生成逼真的人体动作，广泛应用于动画与机器人领域。现有模型在未见文本上表现不佳，主要受限于数据集规模小、多样性不足。为此，我们提出OpenT2M，一个百万级、高质量、开源的动作数据集，包含超过2800小时的人体动作序列。每个序列经过物理可行性验证与多粒度过滤，并配有逐秒级文本标注。我们还设计自动化长时序序列生成流程，支持复杂动作生成。基于此，我们提出MonoFrill预训练模型，无需复杂设计即可实现优异的T2M效果。其核心是2D-PRQ运动分词器，通过将人体划分为生物功能单元，捕捉时空依赖关系。实验表明，OpenT2M显著提升现有T2M模型的泛化能力，2D-PRQ在重建精度和零样本性能上均表现突出。我们期望OpenT2M与MonoFrill能推动该领域在数据质量与基准评测上的进步。
原文摘要 · Abstract (English)
Text-to-motion (T2M) generation aims to create realistic human movements from text descriptions, with promising applications in animation and robotics. Despite recent progress, current T2M models perform poorly on unseen text descriptions due to the small scale and limited diversity of existing motion datasets. To address this problem, we introduce OpenT2M, a million-level, high-quality, and open-source motion dataset containing over 2800 hours of human motion. Each sequence undergoes rigorous quality control through physical feasibility validation and multi-granularity filtering, with detailed second-wise text annotations. We also develop an automated pipeline for creating long-horizon sequences, enabling complex motion generation. Building upon OpenT2M, we introduce MonoFrill, a pretrained motion model that achieves compelling T2M results without complicated designs or technique tricks as "frills". Its core component is 2D-PRQ, a novel motion tokenizer that captures spatiotemporal dependencies by dividing the human body into biology parts. Experiments show that OpenT2M significantly improves generalization of existing T2M models, while 2D-PRQ achieves superior reconstruction and strong zero-shot performance. We expect OpenT2M and MonoFrill will advance the T2M field by addressing longstanding data quality and benchmarking challenges.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。