Artiverse: A Diverse and Physically Grounded Dataset for Articulated Objects

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Iliash, Denys, Liu, Jiayi, Fokin, Egor, Wu, Qirui, Mahdavi-Amiri, Ali, Savva, Manolis, Chang, Angel X.
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917527047634944
author Iliash, Denys
Liu, Jiayi
Fokin, Egor
Wu, Qirui
Mahdavi-Amiri, Ali
Savva, Manolis
Chang, Angel X.
author_facet Iliash, Denys
Liu, Jiayi
Fokin, Egor
Wu, Qirui
Mahdavi-Amiri, Ali
Savva, Manolis
Chang, Angel X.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2605_24403
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Artiverse: A Diverse and Physically Grounded Dataset for Articulated Objects
Iliash, Denys
Liu, Jiayi
Fokin, Egor
Wu, Qirui
Mahdavi-Amiri, Ali
Savva, Manolis
Chang, Angel X.
Computer Vision and Pattern Recognition
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.
title Artiverse: A Diverse and Physically Grounded Dataset for Articulated Objects
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.24403