Research map / Point clouds / Shape and surface completion
PF-Net: Point Fractal Network for 3D Point Cloud Completion
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 |
|---|---|---|---|
| Predict only the missing region while preserving observed points | PF-Net · 13 ShapeNet-Part categories, overall point cloud | Pred → GT error: 1.802 -> 0.555 | Helped |
| Predict only the missing region while preserving observed points | PF-Net · 13 ShapeNet-Part categories, overall point cloud | GT → Pred error: 1.615 -> 0.458 | Helped |
| Predict only the missing region | PF-Net · 13 ShapeNet-Part categories, missing region | Pred → GT error: 4.360 -> 2.426 | Helped |
| Predict only the missing region | PF-Net · 13 ShapeNet-Part categories, missing region | GT → Pred error: 2.603 -> 2.117 | Helped |
| Add the discriminator and adversarial loss (ablation) | PF-Net · 13 ShapeNet-Part categories, overall point cloud | Pred → GT error: 0.572 -> 0.555 | Helped |
| Add the discriminator and adversarial loss (ablation) | PF-Net · 13 ShapeNet-Part categories, missing region | Pred → GT error: 2.483 -> 2.426 | Helped |
| Replace PointNet-MLP with CMLP (ablation) | PointNet classification model · ModelNet40 test | accuracy: 87.2 -> 87.9 | Helped |
| Use the full multi-layer feature aggregation in Our-CMLP (ablation) | PointNet classification model · ModelNet40 test | accuracy: 87.9 -> 88.9 | Helped |
| Replace the single-resolution MLP with CMLP (ablation) | Point cloud completion model · Chair, missing region | Pred → GT error: 2.692 -> 2.587 | Helped |
| Replace the single-resolution MLP with CMLP (ablation) | Point cloud completion model · Table, missing region | Pred → GT error: 2.429 -> 2.250 | Helped |
| Use multi-resolution CMLP instead of single-resolution MLP (ablation) | Point cloud completion model · Chair, missing region | GT → Pred error: 2.384 -> 2.275 | Helped |
| Use multi-resolution CMLP instead of single-resolution MLP (ablation) | Point cloud completion model · Table, missing region | Pred → GT error: 2.429 -> 2.299 | Helped |
Closest papers by meaning
- DC-PCN: Point Cloud Completion Network with Dual-Codebook Guided Quantization (AAAI 2025 · similarity 0.89)
- CDPNet: Cross-Modal Dual Phases Network for Point Cloud Completion (AAAI 2024 · similarity 0.88)
- PointAttN: You Only Need Attention for Point Cloud Completion (AAAI 2024 · similarity 0.88)
- Orthogonal Dictionary Guided Shape Completion Network for Point Cloud (AAAI 2024 · similarity 0.87)
- Position-Aware Guided Point Cloud Completion with CLIP Model (AAAI 2025 · similarity 0.87)
- SymmCompletion: High-Fidelity and High-Consistency Point Cloud Completion with Symmetry Guidance (AAAI 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.