Research map / Point clouds / Shape and surface completion
$p$-Poisson surface reconstruction in curl-free flow from point clouds
Yesom Park, Taekyung Lee, Jooyoung Hahn, Myungjoo Kang
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 |
|---|---|---|---|
| remove the curl-free constraint (ablation) | PINC · SRB | Chamfer/Hausdorff distance | Hurt |
| apply curl-free loss directly on G instead of auxiliary G-tilde (ablation) | PINC · SRB | reconstruction quality | Hurt |
| add minimal area loss (ablation) | PINC · SRB Daratech | Chamfer distance d_C: 4.26 -> 0.37 | Improved |
| add minimal area loss (ablation) | PINC · SRB Daratech | Hausdorff distance d_H: 53.34 -> 7.24 | Improved |
| add minimal area loss (ablation) | PINC · SRB non-daratech shapes | reconstruction quality | No clear effect |
| increase p from 2 to 10 (ablation) | PINC · SRB Gargoyle | Chamfer distance d_C: 3.96 -> 0.22 | Improved |
| increase p from 10 to 100 (ablation) | PINC · SRB Gargoyle | Chamfer distance d_C: 0.22 -> 0.17 | Improved |
| increase p from 100 to infinity (ablation) | PINC · SRB Gargoyle | Chamfer distance d_C: 0.17 -> 0.16 | Improved |
| increase p from 2 to 10 (ablation) | PINC · SRB Anchor | Chamfer distance d_C: 4.32 -> 0.50 | Improved |
| increase p from 10 to 100 (ablation) | PINC · SRB Anchor | Chamfer distance d_C: 0.50 -> 0.31 | Improved |
| use PINC instead of DiGS | PINC · SRB Daratech | Chamfer distance d_C: 0.20 -> 0.37 | Hurt |
| use PINC instead of IGR | PINC · Thingi10K Pumpkin | Hausdorff distance d_H: 1.13 -> 1.90 | 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.
- DiGS — DiGS: Divergence Guided Shape Implicit Neural Representation for Unoriented Point Clouds (CVPR 2022) · better on 6 of 10 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
- Shape As Points: A Differentiable Poisson Solver (NeurIPS 2021 · similarity 0.91)
- GeoUDF: Surface Reconstruction from 3D Point Clouds via Geometry-guided Distance Representation (ICCV 2023 · similarity 0.88)
- POCO: Point Convolution for Surface Reconstruction (CVPR 2022 · similarity 0.87)
- Stochastic Poisson Surface Reconstruction with One Solve using Geometric Gaussian Processes (ICML 2025 · similarity 0.87)
- Neural Splines: Fitting 3D Surfaces With Infinitely-Wide Neural Networks (CVPR 2021 · similarity 0.87)
- Learning Bijective Surface Parameterization for Inferring Signed Distance Functions from Sparse Point Clouds with Grid Deformation (CVPR 2025 · 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.
