AI Paper Atlas

Research map / 3D vision / Face and shape

Fast Globally Optimal and Geometrically Consistent 3D Shape Matching

Paul Roetzer, Florian Bernard

ICCV 2025 · 3D vision › Face and shape · approach: Optimization-based shape matching · 5 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 coupling constraints (ablation)Ours + WKS features · FAUST ablation (10 pairs, 500 triangles)mean geodesic error: 0.2335 -> 0.2253Improved
add coupling constraints (ablation)Ours + Diff3F features · FAUST ablation (10 pairs, 500 triangles)mean geodesic error: 0.1105 -> 0.0511Improved
add coupling constraints (ablation)Ours + ULRSSM features · FAUST ablation (10 pairs, 500 triangles)mean geodesic error: 0.0318 -> 0.0316Improved
use ULRSSM features instead of WKS (ablation)Ours · FAUST ablation (10 pairs, 500 triangles)mean geodesic error: 0.2253 -> 0.0316Improved
use ULRSSM features instead of Diff3F (ablation)Ours · FAUST ablation (10 pairs, 500 triangles)mean geodesic error: 0.0511 -> 0.0316Improved
globally geometrically consistent matching vs SpiderMatchOurs · SHREC'16 cuts (partial-to-full)mean Dirichlet energy: 0.613 -> 0.444Improved
globally geometrically consistent matching vs SpiderMatchOurs · DT4D Intramean geodesic error: 0.027 -> 0.024Improved
globally geometrically consistent matching vs SpiderMatchOurs · SMALmean geodesic error: 0.044 -> 0.044No clear effect
globally geometrically consistent matching vs SpiderMatchOurs · FAUSTmean Dirichlet energy: 1.7 -> 0.46Improved
globally geometrically consistent matching vs SpiderMatchOurs · BeCoSmean Dirichlet energy: 0.81 -> 0.77Improved
replace Gurobi with Mosek as LP solver (ablation)Ours · FAUST runtimeruntimeHurt

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