Research map / Point clouds / Shape and surface completion
Guiding Diffusion-Based Articulated Object Generation by Partial Point Cloud Alignment and Physical Plausibility Constraints
Jens U. Kreber, Joerg Stueckler
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 point cloud guidance loss (ablation) | NAP unguided · PartNet-Mobility test (no category) | E_pc: 0.0564 -> 0.0006 | Improved |
| add point cloud guidance loss (ablation) | NAP unguided · PartNet-Mobility test (no category) | D_pc: 0.2063 -> 0.0435 | Improved |
| add point cloud guidance loss (ablation) | NAP unguided · PartNet-Mobility test (no category) | MMD: 0.0915 -> 0.1540 | Hurt |
| add point cloud guidance loss (ablation) | NAP unguided · PartNet-Mobility test (no category) | 1-NNA: 0.9440 -> 0.9666 | Hurt |
| add penetration and mobility losses to pc guidance (ablation) | PhysNAP pc · PartNet-Mobility test (no category) | E_pen: 0.0018 -> 0.0000 | Improved |
| add penetration and mobility losses to pc guidance (ablation) | PhysNAP pc · PartNet-Mobility test (no category) | E_mob: 0.0031 -> 0.0003 | Improved |
| add penetration and mobility losses to pc guidance (ablation) | PhysNAP pc · PartNet-Mobility test (no category) | E_pc: 0.0006 -> 0.0024 | Hurt |
| add penetration and mobility losses to pc guidance (ablation) | PhysNAP pc · PartNet-Mobility test (no category) | MMD: 0.1540 -> 0.1435 | Improved |
| add penetration loss to pc guidance (ablation) | PhysNAP pc · PartNet-Mobility test (no category) | E_pen: 0.0018 -> 0.0001 | Improved |
| add mobility loss to pc guidance (ablation) | PhysNAP pc · PartNet-Mobility test (no category) | E_mob: 0.0031 -> 0.0004 | Improved |
| add category conditioning (ablation) | PhysNAP pc+pen+mob · PartNet-Mobility test | E_pc: 0.0024 -> 0.0012 | Improved |
| add category conditioning (ablation) | PhysNAP pc+pen+mob · PartNet-Mobility test | 1-NNA: 0.9547 -> 0.9774 | Hurt |
Closest papers by meaning
- SINGAPO: Single Image Controlled Generation of Articulated Parts in Objects (ICLR 2025 · similarity 0.89)
- General Articulated Objects Manipulation in Real Images via Part-Aware Diffusion Process (NeurIPS 2024 · similarity 0.88)
- CAGE: Controllable Articulation GEneration (CVPR 2024 · similarity 0.88)
- MIDGArD: Modular Interpretable Diffusion over Graphs for Articulated Designs (NeurIPS 2024 · similarity 0.87)
- DIPO: Dual-State Images Controlled Articulated Object Generation Powered by Diverse Data (NeurIPS 2025 · similarity 0.87)
- MeshArt: Generating Articulated Meshes with Structure-Guided Transformers (CVPR 2025 · similarity 0.87)
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.
