Artiverse: A Diverse and Physically Grounded Dataset for Articulated Objects
For researchers in 3D vision and robotics, this dataset provides a more diverse and physically grounded resource for articulated object understanding, though it is an incremental contribution over existing datasets.
Artiverse introduces a dataset of 5.4K articulated 3D objects with functional parts, kinematic joints, and physical attributes, reducing annotation time by over 30% via a semi-automated pipeline. It demonstrates utility in part mobility analysis, object generation, and physics-based interaction.
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 and articulated joints 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.