Research map / Point clouds / Shape and surface completion
PartNet: A Recursive Part Decomposition Network for Fine-Grained and Hierarchical Shape Segmentation
Check 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 |
|---|---|---|---|
| Use recursive top-down part decomposition with recursive context and part shape features | PartNet · ShapeNet part dataset | part-wise IoU (%): 86.1 -> 87.4 | Helped |
| Use recursive top-down part decomposition instead of SGPN instance grouping | FineSeg · FineSeg, mean IoU > 0.25 | AP (%): 62.2 -> 84.8 | Helped |
| Use recursive top-down part decomposition instead of SGPN instance grouping | FineSeg · FineSeg, mean IoU > 0.5 | AP (%): 47.0 -> 72.8 | Helped |
| Add recursive context features to node classification and segmentation (ablation) | PartNet · FineSeg, mean IoU > 0.25 | AP (%): 79.2 -> 84.8 | Helped |
| Add recursive context features to node classification and segmentation (ablation) | PartNet · FineSeg, mean IoU > 0.5 | AP (%): 66.0 -> 72.8 | Helped |
| Add part shape features to node classification (ablation) | PartNet · FineSeg, mean IoU > 0.25 | AP (%): 77.6 -> 84.8 | Helped |
| Add part shape features to node classification (ablation) | PartNet · FineSeg, mean IoU > 0.5 | AP (%): 64.9 -> 72.8 | Helped |
Closest papers by meaning
- Learning Fine-Grained Segmentation of 3D Shapes Without Part Labels (CVPR 2021 · similarity 0.91)
- RIM-Net: Recursive Implicit Fields for Unsupervised Learning of Hierarchical Shape Structures (CVPR 2022 · similarity 0.91)
- SegGraph: Leveraging Graphs of SAM Segments for Few-Shot 3D Part Segmentation (NeurIPS 2025 · similarity 0.88)
- PartDistill: 3D Shape Part Segmentation by Vision-Language Model Distillation (CVPR 2024 · similarity 0.87)
- Learning Partonomic 3D Reconstruction from Image Collections (CVPR 2025 · similarity 0.87)
- Learning Hierarchical Image Segmentation For Recognition and By Recognition (ICLR 2024 · 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.