AI Paper Atlas

Research map / 3D vision / Face and shape

Hyper-Network Neural Functional Maps for Unsupervised Robust 3D Shape Matching

Dongliang Cao, Florian Bernard

ECCV 2026 · 3D vision › Face and shape · approach: Optimization-based shape matching · 1 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 hyper-network neural functional map to SSMSMSSMSM · FAUST->SCAPE mesh matchinggeodesic error x100: 9.2 -> 4.6Improved
add hyper-network neural functional map to SSMSMSSMSM · SCAPE->FAUST mesh matchinggeodesic error x100: 7.2 -> 3.2Improved
use ViT hyper-network instead of CNN (ablation)NFM · TOPKIDSgeodesic error x100: 9.6 -> 6.7Improved
use ViT hyper-network instead of MLP (ablation)NFM · TOPKIDSgeodesic error x100: 10.8 -> 6.7Improved
use 2 hidden layers instead of 1 (ablation)NFM · TOPKIDSgeodesic error x100: 10.3 -> 6.7Improved
use 2 hidden layers instead of 3 or 4 (ablation)NFM · TOPKIDSgeodesic error x100: 8.6 -> 6.7 (3 layers); 8.9 -> 6.7 (4 layers)Improved
condition on the correct C instead of swapped C (ablation)NFM hyper-network · SHREC16 HOLESgeodesic error x100: 32.8 -> 4.7Improved
use trained hyper-network instead of random init with test-time optimization (ablation)NFM · SHREC16 HOLESgeodesic error x100: 61.9 -> 4.7Improved
train and test on different datasets (cross-dataset) (ablation)NFM · SHREC16 HOLESgeodesic error x100: 4.7 -> 5.7Hurt
corrupt C with Gaussian noise at inference (ablation)NFM · SHREC16 HOLESgeodesic error x100: 4.7 -> 6.2Hurt
flip signs of 50% eigenvectors at test time (ablation)NFM · SHREC16 HOLESgeodesic error x100: 4.74 -> 4.82No clear effect
use spectral dimension k=128 instead of smaller k (ablation)NFM · SHREC16 HOLESgeodesic error x100: 9.5 -> 4.7 (k=32)Improved

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