Research map / Point clouds / Shape and surface completion
PolyFit: Polygonal Surface Reconstruction From Point Clouds
Liangliang Nan, Peter Wonka
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 plane refinement step (merging near-coplanar segments) (ablation) | PolyFit · Building (Figure 6) | number of candidate faces: 1185 -> 348 | Improved |
| add plane refinement step (ablation) | PolyFit · Building (Figure 6) | optimization run-time: 1.25 seconds -> 0.31 seconds | Improved |
| add plane refinement step (ablation) | PolyFit · Building (Figure 6) | model quality (bumps, face count in top face) | Improved |
| add model complexity term to data fitting and coverage terms (ablation) | PolyFit · Building (Figure 7) | bumps and gaps in model | Improved |
| increase weight of model complexity term (ablation) | PolyFit · Building (Figure 9) | level of model detail | Mixed |
| use data fitting plus coverage terms only on reasonably complete data (ablation) | PolyFit · Complete point clouds | reconstruction quality | No clear effect |
| vary energy weights over a wide range (ablation) | PolyFit · Most examples | reconstruction result | No clear effect |
| increase noise standard deviation to 0.6 meters (ablation) | PolyFit · Synthetic data (Figure 10) | topological accuracy | No clear effect |
| increase noise to a much higher level (ablation) | PolyFit · Synthetic data (Figure 10) | reconstruction error | Hurt |
Later papers that compared with this method
2 later accepted papers report PolyFit as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- WindPoly: Polygonal Mesh Reconstruction via Winding Numbers (ECCV 2024 · better on 5 of 6 shared results)
- PC2WF: 3D Wireframe Reconstruction from Raw Point Clouds (ICLR 2021 · better on 5 of 5 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Surface Reconstruction From Point Clouds: A Survey and a Benchmark (TPAMI 2024 · similarity 0.91)
- Parametric Point Cloud Completion for Polygonal Surface Reconstruction (CVPR 2025 · similarity 0.90)
- A Survey and Benchmark of Automatic Surface Reconstruction From Point Clouds (TPAMI 2024 · similarity 0.90)
- High-Fidelity Lightweight Mesh Reconstruction from Point Clouds (CVPR 2025 · similarity 0.88)
- OffsetOPT: Explicit Surface Reconstruction without Normals (CVPR 2025 · similarity 0.87)
- Hyperbolic-Constraint Point Cloud Reconstruction from Single RGB-D Images (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.
