Artiverse: A Diverse and Physically Grounded Dataset for Articulated Objects

2026-05-23

AI Summary

Existing 3D datasets of articulated objects suffer from limitations in scale, functional annotations, and physical realism, hindering progress in understanding object functionality and interactive behaviors. To address this gap, this work introduces a large-scale dataset comprising 5,400 high-quality, artist-created models across 88 categories, systematically annotated for the first time with functional parts, internal structures, multi-degree-of-freedom kinematic relationships, and physical properties. We propose an efficient semi-automatic annotation pipeline that integrates few-shot segmentation, geometric reasoning, and multi-stage human verification, substantially reducing manual effort while ensuring high annotation fidelity. The dataset demonstrates strong utility in part motion analysis, articulated object generation, and physics-based interaction tasks, significantly advancing research on functional understanding of articulated objects.

Abstract

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.

Problem

• articulated objects
• 3D dataset
• functional modeling
• physics-based interaction
• kinematic relationships

Innovation

• articulated objects
• physically grounded dataset
• semi-automated annotation
• kinematic relationships
• functional modeling