Research map / 3D vision / 3D generation
Articulate3D: Holistic Understanding of 3D Scenes as Universal Scene Description
Anna-Maria Halacheva, Yang Miao, Jan-Nico Zaech, Xi Wang, Luc Van Gool, Danda Pani Paudel
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 |
|---|---|---|---|
| add dense point-wise axis prediction (ablation) | USDNet · Articulate3D motion parameters | AP50+Origin+Axis: 21.9 -> 25.0 | Improved |
| add dense point-wise origin prediction (ablation) | USDNet · Articulate3D motion parameters | AP50+Origin+Axis: 18.2 -> 25.0 | Improved |
| add dense point-wise origin prediction (ablation) | USDNet · Articulate3D motion parameters | AP50+Axis: 38.7 -> 34.6 | Hurt |
| add dense axis and origin prediction to Mask3D baseline (ablation) | Mask3D† · Articulate3D motion parameters | AP50+Origin+Axis: 19.3 -> 25.0 | Improved |
| add point-center-shift auxiliary task and joint dense prediction | Mask3D† · Articulate3D interactable part segmentation | AP50: 30.2 -> 31.1 | Improved |
| replace Mask3D† with USDNet | Mask3D† · Articulate3D movable part segmentation | AP: 22.7 vs 19.8 | Hurt |
| replace Mask3D† with USDNet | Mask3D† · Articulate3D movable part segmentation | AP50: 39.1 -> 41.8 | Improved |
| replace Mask3D† with USDNet | Mask3D† · MultiScan | AP50+Origin+Axis: 23.3 -> 26.0 | Improved |
| replace Mask3D† with USDNet | Mask3D† · SceneFun3D | AP50+Origin+Axis: 22.4 -> 30.5 | Improved |
| pre-train on Articulate3D (ablation) | USDNet · MultiScan | AP50+Origin+Axis: 24.3 -> 26.0 | Improved |
| pre-train on Articulate3D (ablation) | USDNet · MultiScan | AP50: 34.8 -> 40.5 | Improved |
| finetune on Articulate3D | URDFormer · MultiScan | AP50: 22.7 -> 35.1 | Improved |
Closest papers by meaning
- SceneFun3D: Fine-Grained Functionality and Affordance Understanding in 3D Scenes (CVPR 2024 · similarity 0.91)
- Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation Model (ICLR 2025 · similarity 0.91)
- ImageNet3D: Towards General-Purpose Object-Level 3D Understanding (NeurIPS 2024 · similarity 0.89)
- Surprise3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes (NeurIPS 2025 · similarity 0.89)
- IAAO: Interactive Affordance Learning for Articulated Objects in 3D Environments (CVPR 2025 · similarity 0.89)
- Functionality Understanding and Segmentation in 3D Scenes (CVPR 2025 · similarity 0.89)
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.
