AI Paper Atlas

Research map / 3D vision / Human pose estimation

3DGazeNet: Generalizing Gaze Estimation with Weak Supervision from Synthetic Views

Evangelos Ververas, Polydefkis Gkagkos, Jiankang Deng, Michail C Doukas, Jia Guo, Stefanos Zafeiriou

ECCV 2024 · 3D vision › Human pose estimation · approach: Monocular 2D-to-3D pose lifting · 6 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
add multi-view consistency loss to pseudo-label training (ablation)3DGazeNet trained on ITWG · Gaze360 test (cross-dataset)gaze error (degrees): 23.1 -> 18.1Improved
add pseudo-label supervision to multi-view loss (ablation)3DGazeNet trained on ITWG-MV · Gaze360 test (cross-dataset)gaze error (degrees): 47.4 -> 18.1Improved
add multi-view loss on top of GT and pseudo-labels (GC) (ablation)3DGazeNet trained on GC+ITWG · Gaze360 test (cross-dataset)gaze error (degrees): 21.4 -> 17.6Improved
predict dense eye mesh together with gaze vector instead of vector alone (ablation)3DGazeNet within-dataset · Gaze360 within-datasetgaze error (degrees): 9.8 -> 9.6Improved
use dense eye mesh instead of 8 iris landmarks in the multi-view generalization setting (ablation)3DGazeNet trained on ITWG-MV · Gaze360 test (cross-dataset)gaze error (degrees): 18.8 -> 18.1Improved
add mesh target to vector target for generalization (ablation)3DGazeNet trained on ITWG-MV · MPII test (cross-dataset)gaze error (degrees): 8.5 -> 7.6Improved
add ITWG-MV synthetic-view data to ground-truth training3DGazeNet trained on EXG · Gaze360 test (cross-dataset)gaze error (degrees): 22.1 -> 15.4Improved
add AVA multi-view supervision to Gaze360 training3DGazeNet within-dataset · Gaze360 within-datasetgaze error (degrees): 9.6 -> 9.7No clear effect
add large-scale ITWG-MV to Gaze360 training3DGazeNet within-dataset · Gaze360 within-datasetgaze error (degrees): 9.6 -> 9.3Improved
widen head pose range of in-the-wild training data (yaw up to 90 degrees) (ablation)3DGazeNet trained with MPII + ITWG-MV · Gaze360 test across head posesgaze error (degrees)Improved
add ITWG-MV to training for other baselines without noise regularizationRAT/RUDA, CDG/CRGA, PureGaze · MPII and GCgaze error (degrees)No clear effect

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