AI Paper Atlas

Research map / 3D vision / Face and shape

Region-Based Correspondence Between 3D Shapes via Spatially Smooth Biclustering

Matteo Denitto, Simone Melzi, Manuele Bicego, Umberto Castellani, Alessandro Farinelli, Mario A. T. Figueiredo, Yanir Kleiman, Maks Ovsjanikov

ICCV 2017 · 3D vision › Face and shape · approach: Optimization-based shape matching · 9 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 geodesic spatial smoothness prior (ablation)S4B biclustering · FAUST globalmean labelling accuracy: 31.8 -> 94.8Improved
add geodesic spatial smoothness prior (ablation)S4B biclustering · FAUST globalmedian labelling accuracy: 31.26 -> 95.52Improved
add geodesic spatial smoothness prior (ablation)S4B biclustering · FAUST scenario 1mean labelling accuracy: 29.91 -> 97.36Improved
add geodesic spatial smoothness prior (ablation)S4B biclustering · FAUST scenario 3mean labelling accuracy: 32.32 -> 94.25Improved
use S4B instead of SRC for region correspondenceregion-based correspondence · FAUST globalmean labelling accuracy: 86.58 -> 94.8Improved
use S4B instead of SRC for region correspondenceregion-based correspondence · FAUST scenario 2mean labelling accuracy: 85.34 -> 95.73Improved
use S4B instead of BIM with Voronoi segmentationregion-based correspondence · FAUST globalmean labelling accuracy: 93.26 -> 94.8Improved
use S4B instead of BIM with Voronoi segmentationregion-based correspondence · FAUST scenario 1median labelling accuracy: 96.76 -> 97.98Improved
start BIM from S4B labels instead of Voronoi cellsBIM · FAUST globalmean labelling accuracy: 93.26 -> 93.36No clear effect
start BIM from S4B labels instead of Voronoi cellsBIM · FAUST scenario 2mean labelling accuracy: 95.35 -> 94.21Hurt
add S4B region indicators to functional mapsfunctional maps point-wise map estimation · FAUSTcorrect matches vs localization errorImproved
add SRC region indicators to functional maps (versus S4B regions)functional maps point-wise map estimation · FAUSTcorrect matches vs localization errorMixed

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