Research map / Point clouds / Shape and surface completion
Guaranteed Simply Connected Mesh Reconstruction from an Unorganized Point Cloud
Liyan Chen, Jingyi Li, Qixing 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 |
|---|---|---|---|
| add initial spectral triangle orientation (ablation) | Full approach · 2D ablation (Figure 5) | reconstruction quality | Improved |
| add L0-norm robust optimization instead of L1 (ablation) | Full approach · 2D ablation (Figure 5) | reconstruction smoothness | Improved |
| add alternating optimization over a single pass (ablation) | Full approach · 2D ablation (Figure 5) | outlier removal | Improved |
| compare to CrossSDF on thin structures | Ours vs CrossSDF · CrossSDF medical benchmark | Chamfer Distance: reduces CD by 15.8% | Improved |
| compare to CrossSDF on thin structures | Ours vs CrossSDF · CrossSDF medical benchmark | Hausdorff Distance: reduces HD by 9.62% | Improved |
| simply connected topology guarantee versus CrossSDF | Ours vs CrossSDF · Heart (aligned) | connected components: 68 -> 1 | Improved |
| our method versus ScreenedPoisson under outliers | Ours vs ScreenedPoisson · Synthetic bunny 8K+200 | Chamfer Distance: 0.35 -> 0.18 | Improved |
| our method on Alveolis aligned versus CrossSDF | Ours vs CrossSDF · Alveolis (aligned) | Chamfer Distance: 0.35 -> 0.41 | Hurt |
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.
- CrossSDF — CrossSDF: 3D Reconstruction of Thin Structures From Cross-Sections (CVPR 2025) · better on 17 of 19 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
- Learning Delaunay Surface Elements for Mesh Reconstruction (CVPR 2021 · similarity 0.89)
- EdgeMovingNet: Edge-preserving Point Cloud Reconstruction via Joint Geometry Features (CVPR 2025 · similarity 0.87)
- High-Fidelity Lightweight Mesh Reconstruction from Point Clouds (CVPR 2025 · similarity 0.86)
- LAM3D: Large Image-Point Clouds Alignment Model for 3D Reconstruction from Single Image (NeurIPS 2024 · similarity 0.86)
- Hyperbolic-Constraint Point Cloud Reconstruction from Single RGB-D Images (AAAI 2025 · similarity 0.85)
- Consistent Normal Orientation for 3D Point Clouds via Least Squares on Delaunay Graph (CVPR 2025 · similarity 0.85)
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.
