Research map / 3D vision / Face and shape
The Shape Part Slot Machine: Contact-Based Reasoning for Generating 3D Shapes from Parts
Kai Wang, Paul Guerrero, Vladimir G. Kim, Siddhartha Chaudhuri, Minhyuk Sung, Daniel Ritchie
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 |
|---|---|---|---|
| enforce symmetry at test time (ablation) | Ours · PartNet Chair | Fool rate: 8.1 -> 6.4 | Hurt |
| enforce symmetry at test time (ablation) | Ours · PartNet Chair | Frechet distance: 58.9 -> 61.1 | No clear effect |
| enforce symmetry at test time (ablation) | Ours · PartNet Chair | Stability: 68.0 -> 70.1 | No clear effect |
| forbid using parts from same source shape (ablation) | Ours · PartNet Chair | Fool rate: 13.8 -> 6.4 | Hurt |
| forbid using parts from same source shape (ablation) | Ours · PartNet Chair | Stability: 67.4 -> 70.1 | No clear effect |
| slot-graph contact reasoning instead of ComplementMe translation prediction | ComplementMe · PartNet Chair | Rootedness: 90.2 -> 98.1 | Improved |
| slot-graph contact reasoning instead of ComplementMe | ComplementMe · PartNet Chair | Stability: 41.1 -> 70.1 | Improved |
| slot-graph contact reasoning instead of ComplementMe | ComplementMe · PartNet Storage | Frechet distance: 89.8 -> 42.6 | Improved |
| slot-graph contact reasoning instead of ComplementMe | ComplementMe · PartNet Lamp | Frechet distance: 26.0 -> 42.4 | Hurt |
| slot-graph contact reasoning instead of ComplementMe | ComplementMe · PartNet Lamp | Fool rate: 35.8 -> 21.5 | Hurt |
| slot-graph contact reasoning instead of StructureNet | StructureNet · PartNet Chair | Frechet distance: 37.5 -> 61.1 | Hurt |
| slot-graph contact reasoning instead of StructureNet | StructureNet · PartNet Table | Frechet distance: 85.2 -> 61.6 | Improved |
Closest papers by meaning
- Category-Level Multi-Part Multi-Joint 3D Shape Assembly (CVPR 2024 · similarity 0.89)
- Imagine: Image-Guided 3D Part Assembly with Structure Knowledge Graph (AAAI 2025 · similarity 0.87)
- Neural Assembler: Learning to Generate Fine-Grained Robotic Assembly Instructions from Multi-View Images (AAAI 2025 · similarity 0.85)
- 3D Geometric Shape Assembly via Efficient Point Cloud Matching (ICML 2024 · similarity 0.85)
- Generative 3D Part Assembly via Part-Whole-Hierarchy Message Passing (CVPR 2024 · similarity 0.85)
- Two by Two: Learning Multi-Task Pairwise Objects Assembly for Generalizable Robot Manipulation (CVPR 2025 · similarity 0.83)
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.
