As Extended Reality (XR) headsets like the Apple Vision Pro become mainstream, interaction paradigms heavily rely on multimodal inputs, most notably “Gaze+Pinch”. While highly effective, this method requires continuous arm and hand movements. This can cause physical fatigue, feel socially awkward in public spaces, and completely exclude users with severe motor impairments. Existing hands-free alternatives, such as gaze-and-dwell, are notoriously slow. To solve this, we developed Gaze+Blink, a novel, fully hands-free spatial interaction technique designed for both discrete selections and continuous UI manipulations.

The Gaze+Blink system leverages a headset’s built-in eye and head tracking to replace hand gestures, offering distinct interactions based on intentional eye movements:

Crucially, to preserve user privacy, the Gaze+BlinkPlus model does not process raw video from eye cameras; instead, it relies strictly on eye-tracking telemetry, such as pupil size, eye openness, and gaze direction. Tested on uncalibrated users, the model achieved a 75% accuracy rate in filtering out accidental blinks.

Two user studies evaluating Gaze+Pinch, Gaze+Blink, and Gaze+BlinkPlus in a realistic, VisionOS-inspired environment were conducted. Participants completed tasks like navigating menus, entering passwords, and dragging images.

The evaluation yielded several key insights into blink-based spatial interaction:

• Performance Parity: Gaze+Blink matched the industry-standard Gaze+Pinch in task completion speed, perceived workload (NASA-TLX), and overall usability (SUS).
• Accidental Inputs Mitigated: While the baseline Gaze+Blink suffered from a significantly higher error rate due to natural blinks, the machine learning model in Gaze+BlinkPlus successfully reduced these error rates during high-frequency tasks like typing.
• Continuous Task Trade-offs: Blink-based methods exhibited slightly higher error rates during continuous scrolling tasks compared to pinching, but maintained equally fast overall task completion times.
• Polarized UX Feedback: User reception was polarized. Some praised the blink techniques as natural, fast, and physically relaxing, while others found them mentally taxing or prone to misfires.
• Physiological Limitations: A small percentage of users cannot independently close one eye (unilateral apraxia of eyelid closing), which limits their ability to use the drag-and-drop feature.

Ultimately, the paper proves that ML-enhanced blink-based interaction is a viable, high-speed alternative to hand gestures in XR. It represents a significant step forward for spatial computing, providing a discreet input method for confined environments (like airplanes) and offering crucial accessibility to users lacking upper-limb mobility.