AI Paper Atlas

Research map / 3D vision / Face and shape

Fast Markov Random Field Optimisation for Topologically Noisy 3D Shape Matching

Paul Roetzer, Johan Thunberg, Zorah Lähner, Florian Bernard

CVPR 2026 · 3D vision › Face and shape · approach: Optimization-based shape matching

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
use customised alpha-expansion exploiting disjoint label spaces (best label per triangle, no graph cut) instead of standard alpha-expansion (ablation)SM-MRF shape matching · FAUST runtime (five shapes, median)runtimeImproved
add neighbourhood-preserving MRF pairwise cost to feature-based matching, on clean dataSM-MRF with ULRSSM features · FAUST, SMAL, DT4Dgeodesic error vs runtimeImproved
match on topologically noisy shapes with the MRF method versus other methodsSM-MRF · TOPFAUST, SCAPET, TOPKIDSgeodesic errorImproved
add topological noise to the input shapesall shape matching methods · TOPFAUSTgeodesic errorHurt
compare against KernelMatch on speedSM-MRF · FAUST runtimeruntimeHurt
apply concave truncation to pairwise term to ignore very large geodesic distancesSM-MRF · topologically noisy shapesrobustnessImproved

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