AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

A Hierarchical Generative Model for Eye Image Synthesis and Eye Gaze Estimation

Kang Wang, Rui Zhao, Qiang Ji

CVPR 2018 · Image generation › Autoregressive and latent generation · approach: Classical generative image synthesis · 66 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 HGM instead of [33] for image synthesis evaluationEye image synthesis · MPIIGazeError / degree: 7.8 -> 7.6Improved
Use HGM instead of [33] for image synthesis evaluationEye image synthesis · UTMultiviewError / degree: 8.9 -> 8.8Improved
Train the proposed shape estimator with more samples than 3000UnityEye eye shape estimation · UnityEye, 10000 training samplesEye shape prediction error: 1.8 -> 1.4Improved
Add 10000 synthesized image-shape pairs to real training data (ablation)Proposed pupil detector · BioID, deye ≤ 0.05Pupil detection rate: 90.3% -> 92.1%Improved
Add 10000 synthesized image-shape pairs to real training data (ablation)Proposed pupil detector · BioID, deye ≤ 0.10Pupil detection rate: 99.3% -> 99.9%Improved
Add 10000 synthesized image-shape pairs to real training data (ablation)Proposed pupil detector · BioID, deye ≤ 0.25Pupil detection rate: 99.9% -> 99.9%No clear effect
Use HGM instead of CNN[43]Gaze estimation · UnityEye, within-datasetError / degree: 3.4 -> 4.5Hurt
Use HGM instead of CNN[43]Gaze estimation · UnityEye, cross-datasetError / degree: 19.5 -> 15.9Improved
Use HGM instead of CNN[43]Gaze estimation · UTMultiview, within-datasetError / degree: 6.8 -> 8.4Hurt
Use HGM instead of CNN[43]Gaze estimation · UTMultiview, cross-datasetError / degree: 18.3 -> 14.2Improved
Use HGM instead of CNN[43]Gaze estimation · MPIIGaze, within-datasetError / degree: 6.1 -> 7.5Hurt
Use HGM instead of CNN[43]Gaze estimation · MPIIGaze, cross-datasetError / degree: 12.3 -> 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