GazeShift: Unsupervised Gaze Estimation and Dataset for VR
This work addresses the data scarcity and annotation difficulty in VR gaze estimation, providing a label-efficient and real-time solution for VR headset users.
The authors introduce VRGaze, a new dataset of 2.1 million near-eye infrared images from 68 participants for VR gaze estimation. They also propose GazeShift, an unsupervised framework that achieves a 1.84-degree mean error on VRGaze with few-shot calibration and a 7.15-degree person-agnostic error on MPIIGaze with 10x fewer parameters and 35x fewer FLOPs than baselines.
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 infrared 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 1.84-degree mean error on VRGaze. On the remote-camera MPIIGaze dataset, the model achieves a 7.15-degree 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.