Research map / Point clouds / Shape and surface completion
Monge-Ampere Regularization for Learning Arbitrary Shapes From Point Clouds
Chuanxiang Yang, Yuanfeng Zhou, Guangshun Wei, Long Ma, Junhui Hou, Yuan Liu, Wenping Wang
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 Neumann loss alongside Dirichlet and Monge-Ampere losses (ablation) | S2DF learning · Stanford 3D Scanning Repository (ablation) | Chamfer distance mean: 4.533 -> 3.499 | Improved |
| add Dirichlet loss alongside Neumann and Monge-Ampere losses (ablation) | S2DF learning · Stanford 3D Scanning Repository (ablation) | Chamfer distance mean: 3.738 -> 3.499 | Improved |
| add Monge-Ampere loss to Dirichlet and Neumann losses (ablation) | S2DF learning · Stanford 3D Scanning Repository (ablation) | reconstruction success: reconstruction failure (-) -> 3.499 | Improved |
| add non-manifold loss L_non (ablation) | S2DF learning · Stanford 3D Scanning Repository (ablation) | Chamfer distance mean: 3.499 -> 3.499 | No clear effect |
| scale squared distance by K=1000 instead of K=100 (ablation) | S2DF · Stanford 3D Scanning Repository (ablation) | Chamfer distance mean: 6.209 -> 3.499 | Improved |
| scale squared distance by K=1000 instead of K=1 (ablation) | S2DF · Stanford 3D Scanning Repository (ablation) | reconstruction success: reconstruction failure (-) -> 3.499 | Improved |
| increase K from 500 to 1000 (ablation) | S2DF · Stanford 3D Scanning Repository (ablation) | Chamfer distance mean: 3.557 -> 3.499 | Improved |
| increase K from 1000 to 2000 (ablation) | S2DF · Stanford 3D Scanning Repository (ablation) | Chamfer distance mean: 3.499 -> 3.634 | Hurt |
| use SIREN initialization instead of MFGI (ablation) | S2DF · Stanford 3D Scanning Repository (ablation) | Chamfer distance mean: 3.652 -> 3.499 | Improved |
| use S2DF with Monge-Ampere regularization instead of LevelsetUDF | surface reconstruction · MGN (non-watertight, 20 shapes) | Chamfer distance mean: 2.684 -> 2.657 | Improved |
| use S2DF instead of StEik (SDF-based) | surface reconstruction · 3D Scene (500/m2 points) | Chamfer distance mean: 21.25 -> 3.624 | Improved |
| use S2DF instead of LevelSetUDF in runtime (scene-level) | surface reconstruction · 3D Scene scene-level | runtime minutes: 50.44 -> 12.56 | 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.
- DiGS — DiGS: Divergence Guided Shape Implicit Neural Representation for Unoriented Point Clouds (CVPR 2022) · better on 1 of 1 shared result
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 Bijective Surface Parameterization for Inferring Signed Distance Functions from Sparse Point Clouds with Grid Deformation (CVPR 2025 · similarity 0.88)
- Few-Shot Unsupervised Implicit Neural Shape Representation Learning with Spatial Adversaries (ICML 2024 · similarity 0.88)
- A Lightweight UDF Learning Framework for 3D Reconstruction Based on Local Shape Functions (CVPR 2025 · similarity 0.88)
- DUDF: Differentiable Unsigned Distance Fields with Hyperbolic Scaling (CVPR 2024 · similarity 0.88)
- MultiPull: Detailing Signed Distance Functions by Pulling Multi-Level Queries at Multi-Step (NeurIPS 2024 · similarity 0.88)
- Details Enhancement in Unsigned Distance Field Learning for High-fidelity 3D Surface Reconstruction (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.
