GazeShift：面向VR的无监督注视估计与数据集
GazeShift: Unsupervised Gaze Estimation and Dataset for VR
提出一种面向近眼红外图像的无监督注视表征学习框架，通过注意力引导实现注视-外观解耦，并支持轻量少样本校准，为VR场景下的实时注视估计提供了可复用的方法思路。
原文依据 GazeShift, an attention-guided unsupervised framework for learning gaze representations without labeled data.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论注视估计在现代虚拟现实（VR）系统中具有重要作用。尽管远程相机注视估计已取得显著进展，但VR注视研究仍受限于数据稀缺，尤其是缺乏使用现代头显典型的离轴相机配置采集的大规模、精确标注数据集。由于无法保证对预期目标的注视，注视标注十分困难。为应对这些挑战，我们推出了VRGaze，这是首个面向VR的大规模离轴注视估计数据集，包含来自68名参与者的210万张近眼红外图像。我们进一步提出了GazeShift，一种注意力引导的无监督框架，无需标注数据即可学习注视表征。与依赖多视图或三维几何的先前重定向方法不同，GazeShift专为近眼图像设计，在紧凑的实时模型中实现了有效的注视-外观解耦。GazeShift嵌入可通过轻量少样本校准可选地适配个体用户，在VRGaze上达到1.84度的平均误差。在远程相机MPIIGaze数据集上，该模型实现了7.15度的跨人误差，且参数量比基线方法少10倍，浮点运算量少35倍。在VR头显GPU上原生部署时，推理仅需5毫秒。结合已证明的对光照变化的鲁棒性，这些结果凸显了GazeShift作为一种标签高效、实时的VR注视跟踪解决方案。项目代码和VRGaze数据集已在https://github.com/gazeshift3/gazeshift发布。
英文原文摘要 1579 字符
Gaze estimation is instrumental in modern virtual reality (VR) systems. Despite significant progress in remote-camera gaze estimation, VR gaze research remains constrained by data scarcity, particularly the lack of large-scale, accurately labeled datasets captured with the off-axis camera configurations typical of modern headsets. Gaze annotation is difficult since fixation on intended targets cannot be guaranteed. To address these challenges, we introduce VRGaze, the first large-scale off-axis gaze estimation dataset for VR, comprising 2.1 million near-eye infrared images collected from 68 participants. We further propose GazeShift, an attention-guided unsupervised framework for learning gaze representations without labeled data. Unlike prior redirection-based methods that rely on multi-view or 3D geometry, GazeShift is tailored to near-eye imagery, achieving effective gaze-appearance disentanglement in a compact, real-time model. GazeShift embeddings can be optionally adapted to individual users via lightweight few-shot calibration, achieving a 1.84deg mean error on VRGaze. On the remote-camera MPIIGaze dataset, the model achieves a 7.15deg person-agnostic error, doing so with 10x fewer parameters and 35x fewer FLOPs than baseline methods. Deployed natively on a VR headset GPU, inference takes only 5 ms. Combined with demonstrated robustness to illumination changes, these results highlight GazeShift as a label-efficient, real-time solution for VR gaze tracking. Project code and the VRGaze dataset are released at https://github.com/gazeshift3/gazeshift