An Eye-Tracking Dataset for Viewing Distance Categories in Real-World Scenarios
Human-Computer Interaction
Summary
The authors created GazeDepth, a new eye-tracking dataset collected from people wearing a tracker while doing real-world tasks where they look at objects at different distances. Unlike earlier datasets made in labs with fixed viewing distances, GazeDepth includes both fixed and changing distances indoors and outdoors. It records detailed information like eye movements, pupil size, and head motion, along with how far the objects are. The authors found that certain eye features change reliably with distance, and models trained on their data can tell if someone is looking near, middle, or far away. This work helps computers understand how far people are looking in natural settings.
Authors
Dohwa Kim, Yejin Choi, Seungbok Lee, Chi Yoon Jeong, Eunji Park
Abstract
Estimating viewing distance from gaze behavior is essential for understanding user intent and enabling distance-aware interactive systems. However, most existing eye-tracking datasets have been collected in constrained settings, such as laboratory environments or static tasks. Consequently, they only partially capture viewing behaviors in real-world situations where viewing distance changes with natural head and body movements. We introduce GazeDepth, an eye-tracking dataset collected from 19 participants using a wearable tracker during tasks reflecting real-world scenarios. GazeDepth includes fixed-distance viewing scenarios with constant observer-target distances at near (33 cm), middle (50 cm), and far (300 cm), as well as variable-distance viewing scenarios in which participants shift gaze among targets at different depths in indoor and outdoor environments. The dataset provides synchronized gaze data, pupil size, 3D eye-vectors, and head-motion signals, along with distance labels. Statistical analyses showed that distance-related gaze features, such as vergence angle and estimated viewing distance, differed consistently across viewing-distance categories. In addition, classification models trained on GazeDepth further demonstrated that the dataset captures gaze characteristics that distinguish the three viewing-distance categories, supporting gaze-based distance inference and distance-aware interaction in realistic scenarios.