Abstract
Appearance-based gaze estimation (AGE) has achieved remarkable performance in constrained settings, yet we reveal a significant generalization gap where existing AGE models often fail in practical, unconstrained scenarios, particularly those involving facial wearables and poor lighting conditions. We attribute this failure to two core factors: limited image diversity and inconsistent label fidelity across different datasets, especially along the pitch axis. To address these, we propose a robust AGE framework that enhances generalization without requiring additional human-annotated data. First, we expand the image manifold via an ensemble of augmentation techniques, including synthesis of eyeglasses, masks, and varied lighting. Second, to mitigate the impact of anisotropic inter-dataset label deviation, we reformulate gaze regression as a multi-task learning problem, incorporating multi-view supervised contrastive (SupCon) learning, discretized label classification, and eye-region segmentation as auxiliary objectives. To rigorously validate our approach, we curate new benchmark datasets designed to evaluate gaze robustness under challenging conditions, a dimension largely overlooked by existing evaluation protocols. Our MobileNet-based lightweight model achieves generalization performance competitive with the state-of-the-art (SOTA) UniGaze-H, while utilizing less than 1\% of its parameters, enabling high-fidelity, real-time gaze tracking on mobile devices.
Abstract (translated)
基于外观的注视估计（AGE）在受限场景中已取得显著性能，但我们发现其存在明显的泛化差距——现有AGE模型在实际非受限场景中常表现不佳，尤其涉及面部穿戴设备和光照条件恶劣的情况。我们将此归因于两个核心因素：不同数据集间图像多样性有限且标签保真度不一致，尤其在俯仰轴方向。为应对这些问题，我们提出一种无需额外人工标注数据的鲁棒AGE框架以提升泛化能力。首先，通过集成多种增强技术扩展图像流形，包括合成眼镜、口罩及多样化光照。其次，为缓解数据集间各向异性的标签偏差影响，我们将注视回归重构为多任务学习问题，引入多视角监督对比（SupCon）学习、离散化标签分类及眼周区域分割作为辅助目标。为严格验证方法有效性，我们构建了新的基准数据集，专门评估挑战性条件下的注视鲁棒性——这是现有评估协议普遍忽视的维度。基于MobileNet的轻量模型在泛化性能上可与当前最优的UniGaze-H竞争，而参数量不足其1%，实现了移动端高保真实时注视追踪。
URL
https://arxiv.org/abs/2603.26945
