用胶囊网络提升眼神估计的精度与实时性，兼顾可解释性。
CapStARE: Capsule-based Sequential Architecture for Robust and Efficient Gaze Estimation
- 基于冻结的ConvNeXt提取特征，用注意力路由形成胶囊进行结构化面部推理。
- 在ETH-XGaze上误差3.36，MPIIFaceGaze上2.65，支持<10毫秒实时推理。
- 适合需要稳定、高效眼神估计的交互系统，如机器人和辅助设备。
眼神估计对人机交互、社交机器人和辅助系统至关重要。但在非受限环境下实现高精度、可解释且实时的性能仍具挑战。现有外观方法常在空间鲁棒性、计算效率和上下文信息利用间存在权衡。为此，我们提出CapStARE：一种基于胶囊的架构，采用冻结的ConvNeXt骨干网络高效提取特征，通过注意力路由形成胶囊以实现结构化面部推理，并使用双GRU解码器在短时观察窗口内进行轻量级序列建模。该设计保留了可解释的局部-整体面部关系，同时通过局部上下文一致性提升预测稳定性。实验表明，该方法在ETH-XGaze（3.36）、MPIIFaceGaze（2.65）上表现优异，在Gaze360上也具备竞争力（9.06），且支持实时推理（<10毫秒）。结果证明，该方法为真实交互环境下的外观型眼神估计提供了实用而稳健的框架。相关代码与实验结果已公开于：https://github.com/toukapy/capsStare
原文摘要 · Abstract (English)
Human gaze estimation is essential for applications such as human-computer interaction, social robotics, and assistive systems. However, achieving accurate, interpretable, and real-time performance in unconstrained environments remains challenging. Existing appearance-based methods often face trade-offs between spatial robustness, computational efficiency, and effective use of contextual information. To address this, we introduce CapStARE, a capsule-based architecture that combines a frozen ConvNeXt backbone for efficient feature extraction, capsule formation with attention-based routing for structured facial reasoning, and dual GRU decoders for lightweight sequential modeling over short-horizon observation windows. This design preserves interpretable part-whole facial relationships while improving prediction stability through local contextual consistency. Experimental results demonstrate strong performance on ETH-XGaze (3.36) and MPIIFaceGaze (2.65), while also generalizing competitively on Gaze360 (9.06), all with real-time inference (<10 ms). These findings suggest that the proposed method provides a practical and robust framework for appearance-based gaze estimation in real-world interactive environments. The related code and experimental results are publicly available at: https://github.com/toukapy/capsStare
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。