Fovea prediction model in VR
File(s)
Accepted version
Author(s)
Giunchi, Daniele
Bovo, Riccardo
Bhatia, Nitesh
Heinis, Thomas
Steed, Anthony
Type
Conference Paper
Abstract
We propose a lightweight deep learning approach for gaze estimation representing the visual field as three distinct regions: fovea, near, and far peripheral. Each region is modelled using a gaze parameterization gaze regarding angle-magnitude, latitude, or a combination of angle-magnitude-latitude. We evaluated how accurately these representations can predict a user's gaze across the visual field when trained on data from VR headsets. Our experiments confirmed that the latitude model generates gaze predictions with superior accuracy with an average latency compatible with the demanding real-time functionalities of an untethered device. We generated an outperforming ensemble model with a comparable latency.
Date Issued
2024-05-29
Date Acceptance
2024-03-01
Citation
2024 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), 2024, pp.869-870
ISBN
979-8-3503-7450-6
Publisher
IEEE Cmputer Soc
Start Page
869
End Page
870
Journal / Book Title
2024 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW)
Copyright Statement
Copyright © 2024, IEEE. This is the author’s accepted manuscript made available under a CC-BY licence in accordance with Imperial’s Research Publications Open Access policy (www.imperial.ac.uk/oa-policy)
License URL
Source
IEEE Conference on Virtual Reality and 3D User Interfaces (VR)
Subjects
Computer Science
Computer Science, Artificial Intelligence
Computer Science, Cybernetics
Computer Science, Theory & Methods
Computing methodologies
gaze prediction
Human computer interaction (HCI)
Human-centered computing
Interaction paradigms
Machine learning
Machine learning approaches
neural networks
Neural networks
Science & Technology
Technology
Virtual reality
visual attention
Publication Status
Published
Start Date
2024-03-16
Finish Date
2024-03-21
Coverage Spatial
Orlando, FL, USA