提出新校准方法，显著降低眼动追踪残余误差。
Drift Calibration in Geometric Eye Tracking Systems
- 构建统一数据集，评估多种校准修正函数。
- 新神经精炼器将平均角度误差降至0.96度。
- 适合眼动追踪系统优化与交互建模研究者。
几何眼动追踪系统可满足基于注视的交互和多模态研究的空间精度需求，但其测量仍受会话特异性校准误差影响。现有校准方法难以比较，因设备、目标布局和误差定义各不相同。本文构建了一个聚焦校准的数据集，包含12名参与者共163次试验，使用18点拟合网格和32点测试网格，并在统一的空间外推协议下评估全局、局部及复合修正函数。此外，提出一种轻量级神经精炼器，融合互补校准器的排序预测结果。在该可控数据集上，厂商后处理将平均角度误差从1.53°降至1.03°（最强经典复合方法），使用精炼器则降至0.96°。在闭环注视任务中，残余误差越低，性能越高，四种在线修正条件均呈现此趋势。结果为将注视作为行为信号用于交互建模提供了可复现的数据质量基准。
原文摘要 · Abstract (English)
Geometric eye trackers can provide the spatial accuracy required for gaze-based interaction and multimodal studies, but their measurements remain sensitive to residual session-specific calibration error. Research on correcting this error is difficult to compare because methods are typically evaluated with different devices, target layouts, and error definitions. We present a calibration-focused dataset containing 163 trials from 12 participants, with separate 18-point fitting and 32-point test grids, and use it to evaluate global, local, and composite correction functions under a common spatial-extrapolation protocol. We further introduce a lightweight neural refiner that combines ranked predictions from complementary calibrators. On this controlled dataset, post-vendor correction reduces the mean angular error from $1.53^\circ$ to $1.03^\circ$ with the strongest classical composite and to $0.96^\circ$ with the refiner. In a closed-loop gaze task, lower residual error is associated with higher performance across four online correction conditions. These results provide a reproducible data-quality benchmark for using gaze as a behavioral signal in interactive modeling.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。