AI Paper Atlas

Research map / 3D vision / Face and shape

Deep Functional Maps: Structured Prediction for Dense Shape Correspondence

Or Litany, Tal Remez, Emanuele Rodola, Alex Bronstein, Michael Bronstein

ICCV 2017 · 3D vision › Face and shape · approach: Primitive-based shape abstraction · 306 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
train with structured functional-map soft error loss instead of Siamese metric-learning loss (ablation)FMNet · FAUST templates dense correspondencegeodesic errorImproved
use FMNet instead of Chen et al. convex optimization on real scansFAUST real scans inter-class · FAUST real scans (inter)average error (cm): 8.30 -> 4.83Improved
use FMNet instead of Chen et al. on intra-class real scansFAUST real scans intra-class · FAUST real scans (intra)average error (cm): 4.86 -> 2.44Improved
use FMNet instead of Chen et al. on worst error, intra-classFAUST real scans intra-class · FAUST real scans (intra)worst error (cm): 26.57 -> 26.16No clear effect
use the human-specific Stitched Puppet model of Zuffi et al. instead of FMNetFAUST real scans · FAUST real scans (inter)average error (cm): 4.83 -> 3.13Improved
add raw MoNet-style classification loss versus FMNet before refinementFMNet vs MoNet · FAUST synthetic (before refinement)accuracy at zero geodesic errorHurt
add correspondence refinement to FMNet (ablation)FMNet · FAUST syntheticfraction of matches with zero errorImproved
train FMNet on FAUST only and test on SCAPE versus baselines trained on SCAPEFMNet · SCAPE (transfer from FAUST)geodesic errorImproved

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