发表机构
Institute for Neural Computation, University of California San Diego（加州大学圣地亚哥分校神经计算研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文针对几何眼动追踪系统的残留校准误差，构建专用数据集评估校正函数，提出轻量级神经细化器，实验显示其可降低平均角度误差，为注视交互建模提供可复现基准。
AI 中文摘要
几何眼动追踪系统可提供基于注视的交互及多模态研究所需的空间精度，但其测量值仍易受会话特定残留校准误差影响。由于不同方法通常采用不同设备、目标布局及误差定义进行评估，该误差校正研究难以比较。本文提出一个校准专用数据集，包含12名参与者的163次试验，配有独立的18点拟合网格与32点测试网格，采用通用空间外推协议评估全局、局部及复合校正函数；还引入一种轻量级神经细化器，可整合互补校准器的排序预测。在该受控数据集上，厂商后校正将平均角度误差从1.53°降至1.03°，最强经典复合校正降至0.96°，神经细化器则降至0.96°？不对，原文是refiner到0.96°？哦原文是“with the strongest classical composite and to 0.96° with the refiner”，对。在闭环注视任务中，四种在线校正条件下，更低的残留误差对应更高的性能。这些结果为将注视作为交互建模中的行为信号提供了可复现的数据质量基准。
英文摘要
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.
Comments11 pages, 6 figures, 3 tables
