AI Paper Atlas

Research map / 3D vision / Human pose estimation

RT-GENE: Real-Time Eye Gaze Estimation in Natural Environments

Tobias Fischer, Hyung Jin Chang, Yiannis Demiris

ECCV 2018 · 3D vision › Human pose estimation · approach: Learned camera pose estimation · 420 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
train on inpainted images instead of original images with glasses (ablation)Proposed 4 model ensemble · RT-GENE dataset3D gaze error (deg): 8.6 -> 7.7Improved
train on inpainted images instead of original images with glasses (ablation)Single eye [60] · RT-GENE dataset3D gaze error (deg): 14.9 -> 13.4Improved
train on inpainted images instead of original images with glasses (ablation)Spatial weights CNN [61] · RT-GENE dataset3D gaze error (deg): 10.0 -> 8.7Improved
inpaint glasses region instead of leaving original images (ablation)CLNF landmark detector · dataset imagesface detection rate (%): 54.6±24.7 -> 87.7±15.6Improved
inpaint glasses region instead of leaving original images (ablation)ERT landmark detector · dataset imageslandmark error (pixel): 6.6±2.3 -> 5.1±1.3Improved
inpaint glasses region instead of uniform mean-color fill (ablation)ERT landmark detector · dataset imagesface detection rate (%): 59.7±23.0 -> 84.1±17.9Improved
inpaint glasses region instead of uniform mean-color fill (ablation)CLNF landmark detector · dataset imageslandmark error (pixel): 5.6±2.3 -> 5.3±1.8Improved
use an ensemble of 4 models instead of a single model (ablation)Proposed network · MPII Gaze3D gaze error (deg): 4.8 -> 4.3Improved
use a 2 model ensemble instead of a single model (ablation)Proposed network · MPII Gaze3D gaze error (deg): 4.8 -> 4.6Improved
apply ensemble to spatial weights CNN (ablation)Spatial weights CNN [61] · MPII Gaze3D gaze error (deg): 4.8 -> 4.8No clear effect
apply ensemble to spatial weights CNN (ablation)Spatial weights CNN [61] · RT-GENE dataset3D gaze error (deg): 8.7 -> 8.7No clear effect
train on RT-GENE rather than UT Multi-view for cross-dataset test on MPII (ablation)Proposed ensemble · MPII Gaze (cross-dataset)3D gaze error (deg): 8.9 -> 7.7Improved

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