PCFGaze: Physics-Consistent Feature for Appearance-based Gaze Estimation
Yiwei Bao, Feng Lu

TL;DR
This paper introduces PCFGaze, a physics-inspired feature for appearance-based gaze estimation, which improves accuracy and reduces overfitting by aligning gaze features with physical gaze definitions.
Contribution
It proposes a novel Physics-Consistent Feature (PCF) that connects gaze features to physical gaze properties and integrates it into a new gaze estimation framework.
Findings
Improves cross-domain gaze estimation accuracy
Reduces overfitting in gaze models
Enhances understanding of gaze feature physics
Abstract
Although recent deep learning based gaze estimation approaches have achieved much improvement, we still know little about how gaze features are connected to the physics of gaze. In this paper, we try to answer this question by analyzing the gaze feature manifold. Our analysis revealed the insight that the geodesic distance between gaze features is consistent with the gaze differences between samples. According to this finding, we construct the Physics- Consistent Feature (PCF) in an analytical way, which connects gaze feature to the physical definition of gaze. We further propose the PCFGaze framework that directly optimizes gaze feature space by the guidance of PCF. Experimental results demonstrate that the proposed framework alleviates the overfitting problem and significantly improves cross-domain gaze estimation accuracy without extra training data. The insight of gaze feature has…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGaze Tracking and Assistive Technology · Neonatal and fetal brain pathology · Brain Tumor Detection and Classification
