Research map / 3D vision / Human pose estimation
Monocular Free-Head 3D Gaze Tracking With Deep Learning and Geometry Constraints
Wangjiang Zhu, Haoping Deng
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add two-step training (Le+Lh first, then Lg) instead of one-step training with Lg only (ablation) | separate head pose and eyeball model · Own 200-subject gaze dataset | gaze angle error | Improved |
| add the gaze loss Lg after Le+Lh, versus training with Le+Lh only (ablation) | separate head pose and eyeball model · Own 200-subject gaze dataset | gaze angle error | Improved |
| use separate modeling with two-step training instead of MPIIGaze or iTracker style joint models | gaze network · Own 200-subject gaze dataset | gaze angle error | Improved |
| use deeper BN-Inception instead of tiny-AlexNet (ablation) | gaze network · Own 200-subject gaze dataset | gaze angle error (degrees): 5.6 -> 4.3 | Improved |
Closest papers by meaning
- FIFA: Fine-grained Inter-frame Attention for Driver's Video Gaze Estimation (CVPR 2025 · similarity 0.87)
- Enhancing 3D Gaze Estimation in the Wild using Weak Supervision with Gaze Following Labels (CVPR 2025 · similarity 0.86)
- From Feature to Gaze: A Generalizable Replacement of Linear Layer for Gaze Estimation (CVPR 2024 · similarity 0.86)
- GA3CE: Unconstrained 3D Gaze Estimation with Gaze-Aware 3D Context Encoding (CVPR 2025 · similarity 0.86)
- Unsupervised Gaze Representation Learning from Multi-view Face Images (CVPR 2024 · similarity 0.86)
- 3D Prior Is All You Need: Cross-Task Few-shot 2D Gaze Estimation (CVPR 2025 · similarity 0.86)
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.
