Research map / Point clouds / Shape and surface completion
WindPoly: Polygonal Mesh Reconstruction via Winding Numbers
Xin He, Chenlei Lv, Pengdi Huang, Hui Huang
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 |
|---|---|---|---|
| use adaptive spatial partition and polygon-based winding numbers instead of PolyFit exhaustive partition | WindPoly · UrbanBIS | total time: 1707s -> 204s | Improved |
| same pipeline on small CAD models from ABC | WindPoly versus PolyFit and KSR · ABC dataset | total time: 10s (PolyFit) -> 133s (WindPoly) | Hurt |
| reconstruct without normal vectors using polygon-based winding numbers | WindPoly · ABC dataset | Hausdorff distance: 0.111 -> 0.061 (versus KSR) | Improved |
| use WindPoly versus KSR for compactness on building models | WindPoly · Architectural datasets | average point number: 157 -> 549 | Hurt |
| use WindPoly versus IPSR plus simplification | WindPoly · qualitative IPSR comparison | point and face count: 5.0k/9.9k -> 336/168 (points/faces) | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- PolyFit — PolyFit: Polygonal Surface Reconstruction From Point Clouds (ICCV 2017) · better on 5 of 6 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
- GridFormer: Point-Grid Transformer for Surface Reconstruction (AAAI 2024 · similarity 0.85)
- Parametric Point Cloud Completion for Polygonal Surface Reconstruction (CVPR 2025 · similarity 0.85)
- LAM3D: Large Image-Point Clouds Alignment Model for 3D Reconstruction from Single Image (NeurIPS 2024 · similarity 0.84)
- EdgeMovingNet: Edge-preserving Point Cloud Reconstruction via Joint Geometry Features (CVPR 2025 · similarity 0.84)
- High-Fidelity Lightweight Mesh Reconstruction from Point Clouds (CVPR 2025 · similarity 0.84)
- Arbitrary-Scale Point Cloud Upsampling by Voxel-Based Network with Latent Geometric-Consistent Learning (AAAI 2024 · similarity 0.84)
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.
