Research map / Point clouds / Shape and surface completion
Meshing Point Clouds with Predicted Intrinsic-Extrinsic Ratio Guidance
Minghua Liu, Xiaoshuai Zhang, Hao Su
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 |
|---|---|---|---|
| add network-based candidate filtering (ablation) | Ours · ShapeNet | F-score (mu): 0.728 -> 0.872 | Improved |
| add network-based candidate filtering (ablation) | Ours · ShapeNet | F-score (2 mu): 0.882 -> 0.959 | Improved |
| add network-based candidate filtering (ablation) | Ours · ShapeNet | Chamfer distance (x100): 0.110 -> 0.071 | Improved |
| add network-based candidate filtering (ablation) | Ours · ShapeNet | normal similarity: 0.862 -> 0.962 | Improved |
| test on unseen category (leave-one-out training) instead of all categories (ablation) | Ours · ShapeNet | F-score (mu): 0.872 -> 0.870 | No clear effect |
| test on unseen category (leave-one-out training) instead of all categories (ablation) | Ours · ShapeNet | Chamfer distance (x100): 0.071 -> 0.072 | No clear effect |
| increase input point count from 6,400 to 12,800 at test time (ablation) | Ours · ShapeNet | F-score (mu): 0.814 -> 0.872 | Improved |
| increase input point count from 12,800 to 25,600 at test time (ablation) | Ours · ShapeNet | F-score (mu): 0.872 -> 0.907 | Improved |
| increase input point count from 12,800 to 25,600 at test time (ablation) | Ours · ShapeNet | Chamfer distance (x100): 0.071 -> 0.062 | Improved |
| regress geodesic distance directly instead of classifying with intrinsic-extrinsic ratio labels (ablation) | Ours · ShapeNet | candidate classification accuracy: 91.8% -> 65.7% | Hurt |
Closest papers by meaning
- A Survey and Benchmark of Automatic Surface Reconstruction From Point Clouds (TPAMI 2024 · similarity 0.90)
- From Point Clouds to Mesh Using Regression (ICCV 2017 · similarity 0.89)
- Surface Reconstruction From Point Clouds: A Survey and a Benchmark (TPAMI 2024 · similarity 0.89)
- EC-Net: an Edge-aware Point set Consolidation Network (ECCV 2018 · similarity 0.89)
- Learning Delaunay Surface Elements for Mesh Reconstruction (CVPR 2021 · similarity 0.89)
- High-Fidelity Lightweight Mesh Reconstruction from Point Clouds (CVPR 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.
