atlas

Research map / 3D vision / Face and shape

A 3D Morphable Model Learnt From 10,000 Faces

CVPR 2016 · 3D vision › Face and shape · approach: 3D morphable face model regression · 376 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 a larger and more demographically varied training set to construct the 3DMMLSFM-global · MeIn3D test set, face fittingmean per-vertex reconstruction errorHelped
Increase training-set size beyond a few thousand samplesLSFM-global · MeIn3D test set, face fittingmean per-vertex reconstruction errorNo clear effect
Use the demographic-specific LSFM-bespoke models instead of LSFM-globalLSFM models · MeIn3D test setgeneralisation errorMixed
Use demographic-specific models instead of LSFM-globalLSFM models · MeIn3D test setgeneralisation errorHelped
Represent faces with LSFM-global rather than BFMAge classification from 3D shape · MeIn3D test setF-score: 0.78 -> 0.80Helped
Represent faces with LSFM-global rather than Brunton et al. modelAge classification from 3D shape · MeIn3D test setF-score: 0.74 -> 0.80Helped

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