构建大规模角色扮演动作数据集，支持精细文本驱动全身动作生成
RoleMotion: A Large-Scale Dataset towards Robust Scene-Specific Role-Playing Motion Synthesis with Fine-grained Descriptions
- 按场景和角色系统采集，含25个经典场景与110种功能角色
- 涵盖超500种行为、1万+高质量动作序列，配2.7万条细粒度描述
- 适合做文本到动作生成、人机交互、虚拟角色动画的研究者
本文提出RoleMotion，一个大规模人体动作数据集，专为特定场景下的角色扮演与功能性动作设计。现有文本数据集多为分散拼凑，缺乏功能性关联，动作质量参差，文本标注也缺乏细节。相比之下，RoleMotion聚焦场景与角色，包含25个经典场景、110种功能角色、超过500种行为，以及10296条高质量的全身（含手部）动作序列，配有27831条细粒度文本描述。我们构建了比现有方法更强的评估器，验证其可靠性，并在该数据集上评估多种文本到动作生成方法。实验表明，该数据集在文本驱动的全身动作生成任务中展现出高质量与强功能性。
原文摘要 · Abstract (English)
In this paper, we introduce RoleMotion, a large-scale human motion dataset that encompasses a wealth of role-playing and functional motion data tailored to fit various specific scenes. Existing text datasets are mainly constructed decentrally as amalgamation of assorted subsets that their data are nonfunctional and isolated to work together to cover social activities in various scenes. Also, the quality of motion data is inconsistent, and textual annotation lacks fine-grained details in these datasets. In contrast, RoleMotion is meticulously designed and collected with a particular focus on scenes and roles. The dataset features 25 classic scenes, 110 functional roles, over 500 behaviors, and 10296 high-quality human motion sequences of body and hands, annotated with 27831 fine-grained text descriptions. We build an evaluator stronger than existing counterparts, prove its reliability, and evaluate various text-to-motion methods on our dataset. Finally, we explore the interplay of motion generation of body and hands. Experimental results demonstrate the high-quality and functionality of our dataset on text-driven whole-body generation.
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。