AI Paper Atlas

Research map / Point clouds / Shape and surface completion

Learning Delaunay Surface Elements for Mesh Reconstruction

Marie-Julie Rakotosaona, Paul Guerrero, Noam Aigerman, Niloy J. Mitra, Maks Ovsjanikov

CVPR 2021 · Point clouds › Shape and surface completion · approach: Unsupervised shape correspondence · 55 citations (OpenAlex)

Check 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
Use Delaunay surface elements with learned log maps, alignment, and triangle selection rather than the strongest baseline RVEMesh reconstruction · FamousThingi test setNW (%): 9.2 -> 0.4Improved
Use Delaunay surface elements with learned log maps rather than PointTriNetMesh reconstruction · FamousThingi test setCD *1^{e-2}: 0.337 -> 0.326Improved
Use the proposed method rather than IER meshingMesh reconstruction · ShapeNet, 100 random shapesNW (%): 6.96 -> 5.51Improved
Add log-map alignment (ablation)Ours · FamousThingi test setNW (%): 1.07 -> 0.40Improved
Add triangle selection (ablation)Ours · FamousThingi test setNW (%): 10.98 -> 0.40Improved
Add both log-map alignment and triangle selection (ablation)Ours · FamousThingi test setNW (%): 22.51 -> 0.40Improved
Use learned log maps instead of tangent-plane projections (ablation)Ours · FamousThingi test setNW (%): 1.18 -> 0.40Improved
Use learned log maps instead of tangent-plane projection approximation (ablation)Local parameterization · FamousThingi test set, 33 manifold shapesGeodesic distance MSE *1^{e-3}: 1.943 -> 0.471Improved
Use learned log maps instead of the rotation-based approximation (ablation)Local parameterization · FamousThingi test set, 33 manifold shapes2D position MSE *1^{e-2}: 2.835 -> 0.835Improved
Set geodesic neighbor count k to 30 rather than 20 (ablation)Ours · FamousThingi test setNW (%): 4.381 -> 0.485Improved
Set geodesic neighbor count k to 50 rather than 30 (ablation)Ours · FamousThingi test setNW (%): 0.485 -> 0.667Hurt
Set Euclidean neighbor count K to 120 rather than 80 at k=30 (ablation)Ours · FamousThingi test setNW (%): 0.509 -> 0.485Improved

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