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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| train on Artiverse instead of PartNet-Mobility | FPNGroupMot · Part mobility, eval on Artiverse test | segmentation F1: 40.6 -> 50.7 | Improved |
| train on Artiverse instead of PartNet-Mobility | FPNGroupMot · Part mobility, eval on Artiverse test | motion F1 (+MAO): 1.2 -> 10.8 | Improved |
| train on Artiverse instead of PartNet-Mobility | FPNGroupMot · Part mobility, eval on PM test | segmentation F1: 54.2 -> 55.8 | Improved |
| train on Artiverse instead of PartNet-Mobility | FPNGroupMot · Part mobility, eval on PM test | motion F1 (+MAO): 14.3 -> 8.7 | Hurt |
| train on Artiverse instead of PartNet-Mobility | FPNGroupMot · Part mobility, eval on PM test | motion F1 (+MA): 17.0 -> 15.9 | Hurt |
| train on Artiverse instead of PartNet-Mobility | FPNGroupMot · Part mobility, eval on PM test | motion F1 (+M): 22.1 -> 22.4 | No clear effect |
| use SINGAPO trained on Artiverse instead of Articulate-Anything | image-conditioned generation · Eval on Artiverse test | AS-gIoU distance: 1.258 -> 0.822 | Improved |
| use SINGAPO trained on Artiverse instead of Articulate-Anything | image-conditioned generation · Eval on Artiverse test | AOR collision: 0.042 -> 0.009 | Improved |
| use SINGAPO instead of Articulate-Anything | image-conditioned generation · Eval on PM | AS-gIoU distance: 1.179 -> 0.768 | Improved |
| use SINGAPO instead of Articulate-Anything | image-conditioned generation · Eval on PM | AOR collision: 0.024 -> 0.022 | Improved |
| add the semi-automated proposals to manual annotation | Artiverse annotation pipeline · Annotation time, segmentation | manual time saved: 32.0% | Improved |
| add the semi-automated proposals to manual annotation | Artiverse annotation pipeline · Annotation time, motion | manual time saved: 33.5% | Improved |
Closest papers by meaning
- DIPO: Dual-State Images Controlled Articulated Object Generation Powered by Diverse Data (NeurIPS 2025 · similarity 0.87)
- Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation Model (ICLR 2025 · similarity 0.87)
- SINGAPO: Single Image Controlled Generation of Articulated Parts in Objects (ICLR 2025 · similarity 0.87)
- ArtFormer: Controllable Generation of Diverse 3D Articulated Objects (CVPR 2025 · similarity 0.86)
- Building Interactable Replicas of Complex Articulated Objects via Gaussian Splatting (ICLR 2025 · similarity 0.86)
- PhysX-3D: Physical-Grounded 3D Asset Generation (NeurIPS 2025 · similarity 0.86)
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.
