AI Paper Atlas

Research map / 3D vision / Face and shape

Exact Shape Correspondence via 2D graph convolution

Barakeel Fanseu Kamhoua, Lin Zhang, Yongqiang Chen, Han Yang, MA KAILI, Bo Han, Bo Li, James Cheng

NeurIPS 2022 · 3D vision › Face and shape · approach: Optimization-based shape matching · 0 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
use 2D graph convolution (2D-GEM) instead of GRAMPAexact shape matching · TOPKIDS geodesic error 0accuracy: 84.6% -> 90.5%Improved
use 2-hop instead of 1-hop adjacency refinement in GRAMPAGRAMPA · TOPKIDS geodesic error 0accuracy: 60% -> 84.6%Improved
2D-GEM with LMD and 500 eigenvectors instead of DIR-1000nearly-isometric matching · TOSCA geodesic error 0accuracy: 59.8% -> 92.5%Improved
2D-GEM with LMD and 500 eigenvectors instead of DIR-1000nearly-isometric matching · SCAPE geodesic error 0accuracy: 69.5% -> 84.9%Improved
apply GRAMPA to nearly-isometric shapesGRAMPA · SCAPE geodesic error 0accuracy: 84.6% -> 10%Hurt
use more eigenvectors or more iterations2D-GEM · shape matchingaccuracy and running timeMixed
compute only a subset of eigenvectors instead of full spectrum2D-GEM vs GRAMPA · TOPKIDS and SCAPErunning timeImproved
set LMD thresholds arbitrarily large (100) for non-isometric shapes2D-GEM · TOPKIDSaccuracyImproved

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