AI Paper Atlas

Research map / 3D vision / Face and shape

Real Time Eye Gaze Tracking With 3D Deformable Eye-Face Model

Kang Wang, Qiang Ji

ICCV 2017 · 3D vision › Face and shape · approach: Face reflectance and relightable rendering · 120 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 DEFM (eye-face model without head-eye offset) instead of DFM (ablation)gaze estimation with individualized model · Real data, 10 subjectsgaze error (degrees): 5.7 -> 3.5Improved
use DEFM instead of DFM with the average model (ablation)gaze estimation · Real data, 10 subjects (average model)gaze error (degrees): 6.5 -> 4.5Improved
use personal calibration to individualize the model instead of the average model (ablation)DEFM · Real data, 10 subjectsgaze error (degrees): 4.5 -> 3.5Improved
add eye corners to the landmark set (config 2 vs config 1) (ablation)DEFM · Real data, 10 subjectsgaze error (degrees): 4.1 -> 3.5Improved
add eyebrow landmarks to the set (config 2 vs config 5) (ablation)DEFM · Real data, 10 subjectsgaze error (degrees): 4.8 -> 3.5Improved
use manual pupil annotation instead of pupil detector from [30] (ablation)DEFM · Real data, 10 subjectsgaze error (degrees): 3.5 -> 2.5Improved
use starburst pupil detector [29] instead of the fast detector (ablation)DEFM · Real data, 10 subjectsgaze error (degrees) and time (ms): 3.5 -> 3.1 degrees; 2.3 -> 30.0 msMixed
use DEFM instead of DFM under head pose change (ablation)simulated data, different head pose · Simulated data, 1 pixel noisetesting error e3 (degrees): 12.4 vs 13.5Improved
use DEFM instead of DFM under 2D landmark noise (ablation)simulated data · Simulated data, landmark noise sweepgaze error (degrees): margin of 5 degreeImproved
use DEFM instead of DFM for calibration cost (ablation)calibration · Simulated datacalibration time: 40x more time for DFMImproved
propose DEFM over prior landmark-based methodsgaze estimation · ColumbiaGazegaze error (degrees): 8.9 -> 7.1Improved
propose DEFM over prior methods on head movementgaze estimation · EyeDiap (HD camera, head movement)gaze error (degrees): 22.2 -> 16.5Improved

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