Skip to Main content Skip to Navigation
Conference papers

Gaze Prediction using Machine Learning for Dynamic Stereo Manipulation in Games

Abstract : Comfortable, high-quality 3D stereo viewing is becoming a requirement for interactive applications today. Previous research shows that manipulating disparity can alleviate some of the discomfort caused by 3D stereo, but it is best to do this locally, around the object the user is gazing at. The main challenge is thus to develop a gaze predictor in the demanding context of real-time, heavily task-oriented applications such as games. Our key observation is that player actions are highly correlated with the present state of a game, encoded by game variables. Based on this, we train a classifier to learn these correlations using an eye-tracker which provides the ground-truth object being looked at. The classifier is used at runtime to predict object category -- and thus gaze -- during game play, based on the current state of game variables. We use this prediction to propose a dynamic disparity manipulation method, which provides rich and comfortable depth. We evaluate the quality of our gaze predictor numerically and experimentally, showing that it predicts gaze more accurately than previous approaches. A subjective rating study demonstrates that our localized disparity manipulation is preferred over previous methods.
Document type :
Conference papers
Complete list of metadata

Cited literature [4 references]  Display  Hide  Download


https://hal.inria.fr/hal-01290273
Contributor : Team Reves <>
Submitted on : Monday, March 21, 2016 - 8:02:41 PM
Last modification on : Monday, April 9, 2018 - 3:23:37 PM
Long-term archiving on: : Wednesday, June 22, 2016 - 10:32:41 AM

Identifiers

  • HAL Id : hal-01290273, version 1

Collections

Citation

George Alex Koulieris, George Drettakis, Douglas Cunningham, Katerina Mania. Gaze Prediction using Machine Learning for Dynamic Stereo Manipulation in Games. IEEE Virtual Reality, Mar 2016, Greenville, United States. ⟨hal-01290273⟩

Share

Metrics

Record views

283

Files downloads

336