RoMo：面向人体动作生成的大规模、组织丰富的数据集与语义分类体系
RoMo: A Large-Scale, Richly Organized Dataset and Semantic Taxonomy for Human Motion Generation
为文本驱动的人体动作生成提供了大规模、带三级语义分类与细粒度标注的野外动作数据，并配套统一的评测工具箱；做动作生成或动作-文本对齐的研究可直接用它替换小规模动捕数据，或借用其分类体系做按类别的误差分析。
原文依据 We introduce RoMo, a rich, large-scale, carefully curated dataset of in-the-wild human motions that resolves these tradeoffs.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论语言、图像和视频生成建模的成功表明，大规模且精心整理的数据集是构建强能力模型的关键驱动力。然而，3D 人体动作领域却相对滞后，受困于一个并不理想的选择：要么使用小规模高保真动作捕捉数据集，要么使用由静态或低质量序列主导的大规模野外采集数据。我们提出 RoMo，一个丰富、大规模且经过精心整理的野外人体动作数据集，化解了上述取舍。为保证质量，我们引入一条分类体系感知的过滤流水线，激进地剔除静态序列与易出现伪影的序列。每条序列都配有详细描述文本，并按一种新颖的三级语义分类体系组织。这一层级结构提供了首个面向细粒度、逐类别评测的基准，揭示出被全局指标所掩盖的模型优缺点。我们证明，在 RoMo 上训练的模型在达到最优的保真度与多样性的同时，对复杂、细微文本提示的理解也更为出色。最后，我们发布 Motion Toolbox，以统一指标、数据转换与可视化，为可复现、可解释的动作生成研究奠定基础。
英文原文摘要 1264 字符
Success in generative modeling across language, image, and video demonstrates that large, well-curated datasets are the key driver for building capable models. 3D Human motion, however, has lagged behind, constrained by an unsatisfying choice between small, high-fidelity motion capture datasets and large-scale in-the-wild collections dominated by static or low-quality sequences.We introduce RoMo, a rich, large-scale, carefully curated dataset of in-the-wild human motions that resolves these tradeoffs. To ensure quality, we introduce a taxonomy-aware filtering pipeline that aggressively removes static and artifact-prone sequences. Every sequence is annotated with detailed captions and organized by a novel three-level semantic taxonomy. This hierarchical structure provides the first benchmark for fine-grained, per-category evaluation, revealing model strengths and weaknesses obscured by global metrics. We demonstrate that models trained on RoMo achieve state-of-the-art fidelity and diversity while gaining a superior understanding of complex, subtle text prompts. Finally, we release the Motion Toolbox to standardize metrics, data conversion, and visualization, establishing a foundation for reproducible and interpretable motion generation research.