Research map / 3D vision / 3D generation
Arti-PG: A Toolbox for Procedurally Synthesizing Large-Scale and Diverse Articulated Objects with Rich Annotations
Jianhua Sun, Yuxuan Li, Jiude Wei, Longfei Xu, Nange Wang, Yining Zhang, Cewu Lu
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 with Arti-PG synthesized objects | PointTransformer · Part segmentation | mIoU (%): 74.5 -> 79.4 | Improved |
| train with Arti-PG synthesized objects | PointTransformer · Part segmentation | mAcc (%): 89.5 -> 91.3 | Improved |
| train with Arti-PG synthesized objects | SnowFlakeNet · Point cloud completion | Chamfer distance: 11.3 -> 10.4 | Improved |
| train with Arti-PG synthesized objects | NPCS (GAPartNet) · Part pose estimation | 3D mIoU (%): 44.1 -> 48.3 | Improved |
| use Arti-PG instead of PointWOLF augmentation | PointTransformer · Part segmentation | mIoU (%): 75.8 -> 79.4 | Improved |
| train with Arti-PG synthesized objects | Where2Explore · Manipulation pull | success rate (%): 9.3 -> 11.9 | Improved |
| train with Arti-PG synthesized objects | GAPartNet · Manipulation pull | success rate (%): 12.9 -> 16.5 | Improved |
| train with Arti-PG synthesized objects | Where2Act · Manipulation push | success rate (%): 21.4 -> 26.4 | Improved |
| add geometric detail recovery to structure manipulation (ablation) | Arti-PG · Point cloud completion | Chamfer distance: 11.105 -> 10.408 | Improved |
| add geometric detail recovery to structure manipulation (ablation) | Arti-PG · Part segmentation | mIoU (%): 76.7 -> 79.4 | Improved |
| add structure manipulation without geometric recovery (ablation) | Arti-PG · Part segmentation | mIoU (%): 74.5 -> 76.7 | Improved |
| add discrete parameter alteration to CPA (ablation) | Arti-PG · Part segmentation | mIoU (%): 76.5 -> 79.0 | Improved |
Closest papers by meaning
- SINGAPO: Single Image Controlled Generation of Articulated Parts in Objects (ICLR 2025 · similarity 0.90)
- Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation Model (ICLR 2025 · similarity 0.89)
- DIPO: Dual-State Images Controlled Articulated Object Generation Powered by Diverse Data (NeurIPS 2025 · similarity 0.89)
- ArtFormer: Controllable Generation of Diverse 3D Articulated Objects (CVPR 2025 · similarity 0.88)
- Real2Code: Reconstruct Articulated Objects via Code Generation (ICLR 2025 · similarity 0.88)
- IAAO: Interactive Affordance Learning for Articulated Objects in 3D Environments (CVPR 2025 · similarity 0.88)
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.
