Artiverse：一个多样且物理落地的铰接物体数据集
Artiverse: A Diverse and Physically Grounded Dataset for Articulated Objects
为铰接物体理解与生成提供带功能部件、多自由度关节和物理属性（尺度、材质、质量）的标注资源，可直接用于训练部件运动分析、铰接物体生成与物理交互模型；其半自动标注流程（少样本分割+几何推理+多阶段人工校验）也可迁移到其他需要部件级标注的3D数据构建。
原文依据 a semi-automated annotation pipeline that combines few-shot segmentation, geometric reasoning, and multi-stage human verification
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论我们提出 Artiverse，一个多样且物理落地的高质量铰接三维物体数据集，面向真实感功能建模与仿真而设计。Artiverse 包含来自 88 个类别的 5.4K 个人工创作物体，这些物体汇集自多个三维静态资源库。物体标注了功能部件、内部结构、包含多自由度关节的真实运动学关系，以及度量尺度、材质、质量等物理属性。我们开发了一套半自动标注流程，结合少样本分割、几何推理与多阶段人工校验，以实现高质量且高效的标注，将人工标注时间减少 30% 以上。我们在部件运动分析、铰接物体生成与基于物理的交互等任务上展示了 Artiverse 的价值。Artiverse 为推进铰接物体的功能理解提供了数据资源。
英文原文摘要 958 字符
We present Artiverse, a diverse and physically grounded dataset of high-quality articulated 3D objects designed for realistic functional modeling and simulation. Artiverse contains 5.4K human-authored objects across a broad range of 88 categories, aggregated from multiple 3D static repositories. Objects are annotated with functional parts, interior structures, realistic kinematic relationships including multi-DoF joints, and physical attributes such as metric scale, material, and mass. We develop a semi-automated annotation pipeline that combines few-shot segmentation, geometric reasoning, and multi-stage human verification to achieve high-quality and efficient annotation, reducing manual annotation time by over 30%. We demonstrate the value of Artiverse on tasks of part mobility analysis, articulated object generation, and physics-based interaction. Artiverse provides a data resource to advance functional understanding for articulated objects.