Research map / 3D vision / Face and shape
Learning Part Generation and Assembly for Structure-Aware Shape Synthesis
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 reflective symmetry loss for symmetric parts (ablation) | PAGENet part generators · Chair full shape | symmetry measure: 0.77 -> 0.85 | Helped |
| Add reflective symmetry loss for symmetric parts (ablation) | PAGENet part generators · Airplane full shape | symmetry measure: 0.72 -> 0.80 | Helped |
| Indicate the anchor by marking its occupied voxels as -1 rather than using a one-hot vector (ablation) | PAGENet part assembler · Chair part assembly | average IoU: 0.77 -> 0.83; 0.78 -> 0.81; 0.79 -> 0.82; 0.72 -> 0.79 | Helped |
| Use part-wise generation and assembly | PAGENet · Chair random generation | inception score: 6.17 -> 6.55 | Helped |
| Use part-wise generation and assembly | PAGENet · Airplane random generation | inception score: 5.89 -> 6.05 | Helped |
| Use part-wise generation and assembly | PAGENet · Motorbike random generation | inception score: 5.52 -> 5.80 | Helped |
| Use part-wise generation and assembly | PAGENet · Lamp random generation | inception score: 5.45 -> 5.59 | Helped |
| Learn a part assembly prior | PAGENet · Chair part assembly | objective assembly correctness rate: 81.8 -> 90.2 | Helped |
| Learn a part assembly prior | PAGENet · Airplane part assembly | objective assembly correctness rate: 83.7 -> 92.6 | Helped |
| Learn a part assembly prior | PAGENet · Motorbike part assembly | objective assembly correctness rate: 93.6 -> 97.0 | Helped |
| Learn a part assembly prior | PAGENet · Lamp part assembly | objective assembly correctness rate: 91.4 -> 96.8 | Helped |
| Use PAGENet's shape-manifold projection for segmentation | PAGENet · Airplane segmentation | segmentation score: 85.5 -> 83.5 | Hurt |
Closest papers by meaning
- Generative 3D Part Assembly via Part-Whole-Hierarchy Message Passing (CVPR 2024 · similarity 0.90)
- StructEdit: Learning Structural Shape Variations (CVPR 2020 · similarity 0.89)
- PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers (NeurIPS 2025 · similarity 0.89)
- Coarse-to-Fine 3D Part Assembly via Semantic Super-Parts and Symmetry-Aware Pose Estimation (NeurIPS 2025 · similarity 0.89)
- PartGen: Part-level 3D Generation and Reconstruction with Multi-view Diffusion Models (CVPR 2025 · similarity 0.88)
- Imagine: Image-Guided 3D Part Assembly with Structure Knowledge Graph (AAAI 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.