Master's Thesis

EyeDepth: Hands-free Selection in VR

David Martins Correia — 2025

Key information

Authors:

David Martins Correia (David Martins Correia)

Supervisors:

Joaquim Armando Pires Jorge (Joaquim Armando Pires Jorge); Anderson Maciel (Anderson Maciel)

Published in

November 11, 2025

Abstract

With the rapid evolution of virtual reality technology, eye tracking has become a key enabler of natural and intuitive interaction, offering the potential to replace traditional input devices and enhance user immersion. Among its many applications, gaze depth estimation through vergence presents a promising path toward more precise and responsive virtual interactions. Accurate interpretation of user intent based on gaze depth can significantly improve object selection, focus control, and depth-based rendering, enabling more seamless and engaging experiences. However, vergence estimation remains challenged by hardware noise, calibration inconsistencies, and human factors such as fixation instability and eye jitter. This thesis addresses these challenges by developing and evaluating vergence-based gaze interaction techniques that emphasize robustness and usability in cluttered 3D environments. The work was conducted in three stages: assessing vergence reliability, testing gaze confirmation methods, and designing depth-aware selection techniques. Each stage built upon empirical insights from the previous one, progressively forming a complete gaze interaction framework. The proposed techniques were tested in controlled but visually complex virtual environments, highlighting how depth-aware strategies can mitigate gaze inaccuracies while maintaining comfort and efficiency. Empirical evaluations demonstrated robust depth estimation, higher selection accuracy compared to baseline gaze input, and improved user comfort through reduced gaze instability and task-induced fatigue. The findings contribute to the design of stable and precise gaze-based interfaces that operate effectively even under depth ambiguity, laying the groundwork for future adaptive and dynamic gaze interaction systems.

Publication details

Authors in the community:

Supervisors of this institution:

Fields of Science and Technology (FOS)

electrical-engineering-electronic-engineering-information-engineering - Electrical engineering, electronic engineering, information engineering

Publication language (ISO code)

eng - English

Rights type:

Embargo lifted

Date available:

September 23, 2026

Institution name

Instituto Superior Técnico