Research map / 3D vision / 3D generation
NAP: Neural 3D Articulated Object Prior
Jiahui Lei, Congyue Deng, Bokui Shen, Leonidas Guibas, Kostas Daniilidis
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 |
|---|---|---|---|
| remove positional encoding (ablation) | NAP · PartNet-Mobility, Part SDF Shape | MMD: 0.0268 -> 0.0282 | Hurt |
| remove positional encoding (ablation) | NAP · PartNet-Mobility, Part SDF Shape | COV: 0.4944 -> 0.4766 | Hurt |
| remove positional encoding (ablation) | NAP · PartNet-Mobility, Part Retrieval Shape | COV: 0.5234 -> 0.5457 | No clear effect |
| replace edge attention with mean pooling (ablation) | NAP · PartNet-Mobility, Part SDF Shape | MMD: 0.0268 -> 0.0286 | Hurt |
| replace edge attention with mean pooling (ablation) | NAP · PartNet-Mobility, Part Retrieval Shape | 1-NNA: 0.5412 -> 0.5568 | Hurt |
| replace graph convolution with global pooling (ablation) | NAP · PartNet-Mobility, Part SDF Shape | MMD: 0.0268 -> 0.0331 | Hurt |
| replace graph convolution with global pooling (ablation) | NAP · PartNet-Mobility, Part SDF Shape | 1-NNA: 0.5690 -> 0.6570 | Hurt |
| replace graph convolution with global pooling (ablation) | NAP · PartNet-Mobility, Part Retrieval Shape | COV: 0.5234 -> 0.4722 | Hurt |
| diffuse directly in articulation graph space instead of latent space | NAP · PartNet-Mobility, Part SDF Shape | MMD: 0.0314 -> 0.0268 | Improved |
| diffuse directly in articulation graph space instead of latent space | NAP · PartNet-Mobility, Part Retrieval Shape | 1-NNA: 0.6102 -> 0.5412 | Improved |
| autoregressive generation instead of VAE | NAP · PartNet-Mobility, Part SDF Shape | 1-NNA: 0.8085 -> 0.6860 | Improved |
| VAE instead of auto-decoding | NAP · PartNet-Mobility, Part SDF Shape | COV: 0.1871 -> 0.3497 | Improved |
Closest papers by meaning
- CAGE: Controllable Articulation GEneration (CVPR 2024 · similarity 0.91)
- DIPO: Dual-State Images Controlled Articulated Object Generation Powered by Diverse Data (NeurIPS 2025 · similarity 0.90)
- SINGAPO: Single Image Controlled Generation of Articulated Parts in Objects (ICLR 2025 · similarity 0.89)
- ArtFormer: Controllable Generation of Diverse 3D Articulated Objects (CVPR 2025 · similarity 0.88)
- General Articulated Objects Manipulation in Real Images via Part-Aware Diffusion Process (NeurIPS 2024 · similarity 0.88)
- Real2Code: Reconstruct Articulated Objects via Code Generation (ICLR 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.
