AI Paper Atlas

Research map / 3D vision / Face and shape

Joint Face Alignment and 3D Face Reconstruction with Application to Face Recognition

Feng Liu, Qijun Zhao, Xiaoming Liu, Dan Zeng

TPAMI 2018 · 3D vision › Face and shape · approach: 3D morphable face model regression · 116 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 linear instead of nonlinear regressors (ablation)joint alignment and reconstruction · BU3DFE 3D reconstructionMAE: 1.92 -> 1.87Improved
use nonlinear (CNN feature, MLP) regressors instead of linear (ablation)joint alignment and reconstruction · AFLW alignmentNME: 4.49 -> 4.16Improved
use nonlinear instead of linear regressors (ablation)joint alignment and reconstruction · AFLW2000-3D alignmentNME: 4.61 -> 4.20Improved
fuse 3D shape matching with 2D matcherCenterLoss · Multi-PIE exp. 1 (+-90 degrees)accuracy (%): 48.2 -> 63.7Improved
fuse 3D shape matching with 2D matcherLDF-Net · Multi-PIE exp. 1 (+-90 degrees)accuracy (%): 65.3 -> 70.4Improved
fuse 3D shape matching with 2D matcherVGG · Multi-PIE exp. 1 (avg)accuracy (%): 79.5 -> 85.5Improved
fuse 3D shape matching with 2D matcherLightenedCNN · Multi-PIE exp. 1 (avg)accuracy (%): 68.8 -> 75.1Improved
fuse 3D shape matching with 2D matcherCenterLoss · Multi-PIE exp. 1 (+-45 degrees)accuracy (%): 98.8 -> 97.8Hurt
fuse 3D shape matching with 2D matcherLDF-Net · Multi-PIE exp. 1 (avg)accuracy (%): 90.2 -> 90.9Improved
fuse 3D shape matching with 2D matcherCenterLoss · Multi-PIE exp. 2 (expressions, avg)accuracy (%): 78.7 -> 81.4Improved
fuse 3D shape matching with 2D matcherCenterLoss · CFP frontal-profile verificationaccuracy (%): 69.27 -> 72.99Improved
fuse 3D shape matching with 2D matcherCenterLoss · CFP frontal-frontal verificationaccuracy (%): 86.43 -> 89.21Improved

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