AI Paper Atlas

Research map / 3D vision / Face and shape

Gaussian Process Morphable Models

Marcel Lüthi, Thomas Gerig, Christoph Jud, Thomas R. Vetter

TPAMI 2017 · 3D vision › Face and shape · approach: Optimization-based shape matching · 244 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 anisotropic multiscale kernel instead of single Gaussian kernel (ablation)GPMM ulna model · Ulna shape model (full model)specificity: 5.8 -> 2.9Improved
use anisotropic multiscale kernel instead of isotropic multiscale kernel (ablation)GPMM ulna model · Ulna shape model (full model)compactness: 317.0 -> 137.1Improved
use anisotropic multiscale kernel instead of single Gaussian kernel (ablation)GPMM ulna model · Ulna shape model (full model)compactness: 299.1 -> 137.1Improved
use isotropic multiscale kernel instead of single Gaussian kernel (ablation)GPMM ulna model · Ulna shape model (full model)specificity: 5.8 -> 6.1Hurt
use multiscale or anisotropic kernel instead of single Gaussian kernel (ablation)GPMM · Ulna surface registrationgeneralizationImproved
add smooth additive deformation or localized kernel to ASM shape model (ablation)Active Shape Model · Ulna ASM fitting (leave-one-out)fitting accuracyMixed
add 4 landmark constraints via posterior model to extended ASM (ablation)GPMM Active Shape Model · Ulna ASM fitting (leave-one-out)fitting accuracyImproved
use anisotropic model instead of Gaussian or multiscale in image registration (ablation)GPMM · Ulna image registrationsurface distanceImproved
use multi-resolution B-spline instead of GPMMimage registration · Ulna image registrationaccuracy: 500 parameters vs 37926 parametersHurt
use single-level B-spline instead of GPMMimage registration · Ulna image registrationaccuracy and robustnessHurt
increase Nystrom points from n=200 to n=1000 for slowly decaying eigenfunction phi_40 (ablation)Nystrom eigenfunction approximation · 1D Gaussian kernel (analytic)eigenfunction approximation quality: n=200 -> n=1000Improved
cover 99% of variance with very wiggly kernel (sigma=0.005) (ablation)low-rank GP approximation · 1D exampleapproximation error: slightly larger than 1%Hurt

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