OpenT2M：基于开源、大规模、高质量数据的无冗余运动生成
OpenT2M: No-frill Motion Generation with Open-source, Large-scale, High-quality Data
2D-PRQ 按人体生物学部位划分并捕捉时空依赖的运动分词器，可复用于人体动作表示与长时序运动合成；OpenT2M 的物理可行性校验与多粒度过滤流程，为构建高质量人体运动数据提供可借鉴的自动化管线。
原文依据 Its core component is 2D-PRQ, a novel motion tokenizer that captures spatiotemporal dependencies by dividing the human body into biology parts.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论文本到运动（T2M）生成旨在根据文本描述创建逼真的人体运动，在动画与机器人领域具有广阔应用前景。尽管近期取得了进展，现有 T2M 模型由于已有运动数据集规模小、多样性有限，在未见过的文本描述上表现不佳。为解决这一问题，我们提出 OpenT2M，一个百万级、高质量、开源的运动数据集，包含超过 2800 小时的人体运动。每条序列都经过物理可行性验证与多粒度过滤的严格质量控制，并配有逐秒的详细文本标注。我们还开发了一套用于生成长时程序列的自动化管线，从而支持复杂运动生成。基于 OpenT2M，我们提出 MonoFirll，一个预训练运动模型，无需复杂设计或被称为“冗余”的技术技巧即可取得有说服力的 T2M 结果。其核心组件是 2D-PRQ，一种新颖的运动分词器，通过将人体划分为生物学部位来捕捉时空依赖关系。实验表明，OpenT2M 显著提升了现有 T2M 模型的泛化能力，而 2D-PRQ 实现了更优的重建效果与强大的零样本性能。我们期望 OpenT2M 与 MonoFirll 能够通过解决长期存在的数据质量与基准评测难题，推动 T2M 领域的发展。项目主页为 https://research.beingbeyond.com/opent2m
英文原文摘要 1419 字符
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 MonoFirll, 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 MonoFirll will advance the T2M field by addressing longstanding data quality and benchmarking challenges. The project page is https://research.beingbeyond.com/opent2m