AI Paper Atlas

Research map / 3D vision / 3D generation

Artiverse: A Diverse and Physically Grounded Dataset for Articulated Objects

Denys Iliash, Jiayi Liu, Egor Fokin, Qirui Wu, Ali Mahdavi Amiri, Manolis Savva, Angel X. Chang

CVPR 2026 · 3D vision › 3D generation · approach: Hand-object interaction generation · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
train on Artiverse instead of PartNet-MobilityFPNGroupMot · Part mobility, eval on Artiverse testsegmentation F1: 40.6 -> 50.7Improved
train on Artiverse instead of PartNet-MobilityFPNGroupMot · Part mobility, eval on Artiverse testmotion F1 (+MAO): 1.2 -> 10.8Improved
train on Artiverse instead of PartNet-MobilityFPNGroupMot · Part mobility, eval on PM testsegmentation F1: 54.2 -> 55.8Improved
train on Artiverse instead of PartNet-MobilityFPNGroupMot · Part mobility, eval on PM testmotion F1 (+MAO): 14.3 -> 8.7Hurt
train on Artiverse instead of PartNet-MobilityFPNGroupMot · Part mobility, eval on PM testmotion F1 (+MA): 17.0 -> 15.9Hurt
train on Artiverse instead of PartNet-MobilityFPNGroupMot · Part mobility, eval on PM testmotion F1 (+M): 22.1 -> 22.4No clear effect
use SINGAPO trained on Artiverse instead of Articulate-Anythingimage-conditioned generation · Eval on Artiverse testAS-gIoU distance: 1.258 -> 0.822Improved
use SINGAPO trained on Artiverse instead of Articulate-Anythingimage-conditioned generation · Eval on Artiverse testAOR collision: 0.042 -> 0.009Improved
use SINGAPO instead of Articulate-Anythingimage-conditioned generation · Eval on PMAS-gIoU distance: 1.179 -> 0.768Improved
use SINGAPO instead of Articulate-Anythingimage-conditioned generation · Eval on PMAOR collision: 0.024 -> 0.022Improved
add the semi-automated proposals to manual annotationArtiverse annotation pipeline · Annotation time, segmentationmanual time saved: 32.0%Improved
add the semi-automated proposals to manual annotationArtiverse annotation pipeline · Annotation time, motionmanual time saved: 33.5%Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy