Related Experiment Video
Updated: May 14, 2026
09:27
Using Eye Movements Recorded in the Visual World Paradigm to Explore the Online Processing of Spoken Language
Published on: October 13, 2018
Estimating the gaze of a virtuality human
David J Roberts1, John Rae, Tobias W Duckworth
1University of Salford. d.j.roberts@salford.ac.uk
IEEE Transactions on Visualization and Computer Graphics
|February 23, 2013
Summary
Eye-gaze estimation from virtual humans can achieve social interaction accuracy. However, this accuracy depends heavily on gaze pose and camera arrangement with current Video Based Reconstruction methods.
Area of Science:
- Human-Computer Interaction
- Computer Vision
- Virtual Reality
Background:
- Immersive Virtuality Telepresence aims to faithfully convey remote participants' appearance and focus of attention in shared 3D contexts.
- Accurate eye-gaze estimation is crucial for natural social interaction in virtual environments.
Purpose of the Study:
- To determine if eye-gaze can be estimated from virtual humans with accuracy sufficient for social interaction.
- To assess the reliability of eye-gaze estimation across various gaze poses and camera arrangements in everyday settings.
Main Methods:
- 22 participants rotated static 3D virtual humans reconstructed from surround images to find the perceived gaze direction.
- Absolute angular error in eye-gaze estimation was measured and compared to natural social gaze behavior.
- Independent variables included subject's eye, head, and body orientation, and the subset of cameras used for reconstruction.
Main Results:
- Virtuality can reproduce eye-gaze with accuracy useful for social interaction.
- The accuracy of Video Based Reconstruction (VBR) for eye-gaze is highly dependent on the combination of gaze pose and camera arrangement.
- Analysis revealed significant relationships between gaze pose, reconstruction method, and camera setup.
Conclusions:
- Current VBR methods for eye-gaze estimation in virtual humans require optimization for more flexible camera arrangements.
- The findings are relevant for developing expressive, socially and spatially situated virtual meetings.
- Applications include human interaction studies, gaming, and virtual production in film and TV.
Related Concept Videos
01:15Depth Perception and Spatial Vision
Depth perception is the ability to perceive objects three-dimensionally. It relies on two types of cues: binocular and monocular. Binocular cues depend on the combination of images from both eyes and how the eyes work together. Since the eyes are in slightly different positions, each eye captures a slightly different image. This disparity between images, known as binocular disparity, helps the brain interpret depth. When the brain compares these images, it determines the distance to an object.
01:05Estimation of the Physical Quantities
On many occasions, physicists, other scientists, and engineers need to make estimates of a particular quantity. These are sometimes referred to as guesstimates, order-of-magnitude approximations, back-of-the-envelope calculations, or Fermi calculations. The physicist Enrico Fermi was famous for his ability to estimate various kinds of data with surprising precision. Estimating does not mean guessing a number or a formula at random. Instead, estimation means using prior experience and sound...