AI Paper Atlas

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

TPAMI 2025 · Point clouds › Shape and surface completion · approach: Distance-function surface reconstruction · 7 citations (OpenAlex)

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 changedWhereMeasuredEffect
add Neumann loss alongside Dirichlet and Monge-Ampere losses (ablation)S2DF learning · Stanford 3D Scanning Repository (ablation)Chamfer distance mean: 4.533 -> 3.499Improved
add Dirichlet loss alongside Neumann and Monge-Ampere losses (ablation)S2DF learning · Stanford 3D Scanning Repository (ablation)Chamfer distance mean: 3.738 -> 3.499Improved
add Monge-Ampere loss to Dirichlet and Neumann losses (ablation)S2DF learning · Stanford 3D Scanning Repository (ablation)reconstruction success: reconstruction failure (-) -> 3.499Improved
add non-manifold loss L_non (ablation)S2DF learning · Stanford 3D Scanning Repository (ablation)Chamfer distance mean: 3.499 -> 3.499No clear effect
scale squared distance by K=1000 instead of K=100 (ablation)S2DF · Stanford 3D Scanning Repository (ablation)Chamfer distance mean: 6.209 -> 3.499Improved
scale squared distance by K=1000 instead of K=1 (ablation)S2DF · Stanford 3D Scanning Repository (ablation)reconstruction success: reconstruction failure (-) -> 3.499Improved
increase K from 500 to 1000 (ablation)S2DF · Stanford 3D Scanning Repository (ablation)Chamfer distance mean: 3.557 -> 3.499Improved
increase K from 1000 to 2000 (ablation)S2DF · Stanford 3D Scanning Repository (ablation)Chamfer distance mean: 3.499 -> 3.634Hurt
use SIREN initialization instead of MFGI (ablation)S2DF · Stanford 3D Scanning Repository (ablation)Chamfer distance mean: 3.652 -> 3.499Improved
use S2DF with Monge-Ampere regularization instead of LevelsetUDFsurface reconstruction · MGN (non-watertight, 20 shapes)Chamfer distance mean: 2.684 -> 2.657Improved
use S2DF instead of StEik (SDF-based)surface reconstruction · 3D Scene (500/m2 points)Chamfer distance mean: 21.25 -> 3.624Improved
use S2DF instead of LevelSetUDF in runtime (scene-level)surface reconstruction · 3D Scene scene-levelruntime minutes: 50.44 -> 12.56Improved

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy