Research map / Point clouds / Point cloud classification
PIE-NET: Parametric Inference of Point Cloud Edges
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 |
|---|---|---|---|
| Use parametric curve proposals and ranking instead of edge-point classification alone | PIE-Net vs. EC-Net · ABC test set | ECD: 0.0360 -> 0.0088 | Helped |
| Use parametric curve proposals and ranking instead of edge-point classification alone | PIE-Net vs. EC-Net · ABC test set | IoU: 0.3561 -> 0.6223 | Helped |
| Increase proposal sampling radius to R'=1.5R (ablation) | PIE-Net · ABC test set | ECD: 0.0136 -> 0.0326 | Hurt |
| Increase proposal sampling radius to R'=3R (ablation) | PIE-Net · ABC test set | ECD: 0.0136 -> 0.0824 | Hurt |
| Lower corner threshold to τc=0.8 (ablation) | PIE-Net · ABC test set | ECD: 0.0136 -> 0.0150 | Hurt |
| Raise corner threshold to τc=0.95 (ablation) | PIE-Net · ABC test set | ECD: 0.0136 -> 0.0144 | Hurt |
| Lower edge threshold to τe=0.6 (ablation) | PIE-Net · ABC test set | ECD: 0.0136 -> 0.0163 | Hurt |
| Raise edge threshold to τe=0.8 (ablation) | PIE-Net · ABC test set | ECD: 0.0136 -> 0.0149 | Hurt |
| Add edge and corner offset regression (ablation) | PIE-Net · ABC test set | ECD: 0.0186 -> 0.0136 | Helped |
Closest papers by meaning
- NerVE: Neural Volumetric Edges for Parametric Curve Extraction From Point Cloud (CVPR 2023 · similarity 0.90)
- PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation (CVPR 2017 · similarity 0.88)
- DeepLA-Net: Very Deep Local Aggregation Networks for Point Cloud Analysis (CVPR 2025 · similarity 0.88)
- EdgeMovingNet: Edge-preserving Point Cloud Reconstruction via Joint Geometry Features (CVPR 2025 · similarity 0.87)
- LinNet: Linear Network for Efficient Point Cloud Representation Learning (NeurIPS 2024 · similarity 0.86)
- CurveCloudNet: Processing Point Clouds with 1D Structure (CVPR 2024 · similarity 0.86)
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.