Answers are grounded in this paper and cite their sources.
Video-oculography (VOG) enables the objective measurement of eye movements for clinically-relevant tasks, but wide-spread application via consumer devices requires sub-mm and sub-degree head pose tracking to compensate for uncontrolled head and camera motion. We consider approaches: Apple's ARKit, which fuses TrueDepth IR and RGB but is restricted to iPhones with Face ID hardware, and Pixel3DMM, a monocular RGB-only method that could generalize to any camera but has not been validated against depth-sensor ground truth. Head pose from both trackers was aligned frame-by-frame and split into head-still and head-moving portions. We measured peak-to-peak change at each head-movement event (E→F vertical, G→H horizontal), drift as the endpoint difference across the head-still segment, and saccade response as mean peak-to-peak across detected vertical and horizontal saccade events.
No takes yet. Share an insight, caveat, or question.
Narsipur et al. (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: