SwEYEpinch: Exploring Intuitive, Efficient Text Entry for Extended Reality via Eye and Hand Tracking

📅 2026-04-03
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
Existing text input methods in extended reality (XR) suffer from low efficiency and high cognitive load, falling short of the performance offered by physical keyboards or touchscreens. This work proposes a novel input paradigm that integrates eye-gaze-based swipe gestures with sustained pinch-hand gestures. By incorporating language modeling during swiping, an in-gesture cancellation mechanism, a low-latency decoder, and spatiotemporal dynamic time warping, the system achieves high accuracy while substantially improving input speed. User studies demonstrate that participants reached a peak typing rate of 64.7 words per minute after 30 training sessions—significantly outperforming conventional key-by-key selection, finger-tap-only, and hand-swipe-only approaches. Moreover, users reported strong preference for the method and exhibited durable learning effects over time.
📝 Abstract
Despite steady progress, text entry in Extended Reality (XR) often remains slower and more effortful than typing on a physical keyboard or touchscreen. We explore a simple idea: use gaze to swipe through a virtual keyboard for the fast, low-effort where and a manual pinch held throughout the swipe for the when, extending and validating it through a series of user studies. We first show that a basic version including a low-latency decoder with spatiotemporal Dynamic Time Warping and fixation filtering outperforms selecting individual keys sequentially, either by finger tapping each or gazing at each while pinching. We then add mid-swipe prediction and in-gesture cancellation, improving words per minute (WPM) without hurting accuracy. We show that this approach is faster and more preferred than previous gaze-swipe approaches, finger tapping with prediction, or hand swiping with the same additions. Furthermore, a seven-day, 30-session study demonstrates sustained learning, with peak performance reaching 64.7 WPM.
Problem

Research questions and friction points this paper is trying to address.

Extended Reality
text entry
eye tracking
hand tracking
input efficiency
Innovation

Methods, ideas, or system contributions that make the work stand out.

eye-hand interaction
gaze-swipe typing
Extended Reality text entry
Dynamic Time Warping
mid-swipe prediction
🔎 Similar Papers
No similar papers found.
Z
Ziheng "Leo" Li
Department of Computer Science, Columbia University, New York, NY, USA
X
Xichen He
Department of Computer Science, Columbia University, New York, NY, USA
M
Mengyuan "Millie" Wu
Department of Computer Science, Columbia University, New York, NY, USA
Z
Zeyi Tong
Department of Computer Science, Columbia University, New York, NY, USA
H
Haowen Wei
Department of Computer Science, Columbia University, New York, NY, USA
B
Benjamin Yang
Department of Computer Science, Columbia University, New York, NY, USA
Steven Feiner
Steven Feiner
Professor of Computer Science, Columbia University
Human-Computer InteractionAugmented RealityVirtual Reality3D User InterfacesWearable Computing
Paul Sajda
Paul Sajda
Columbia University
neural engineeringneuroengineeringneuroimagingmachine learning