Looking Across the Uncanny Valley: Enhanced Gaze Modeling for Virtual Characters

teaserImage

People

Abstract

Eye movements play a key role in human communication, yet they remain a significant stumbling block for humanoid animation. Computer generated avatars currently lack realistic gaze, which subconsciously distracts viewers and thereby detracts from the usefulness of the many applications that employ these graphical actors. This project represents a collaboration between two investigators with complementary skills who will tackle the problem by developing a holistic model of gaze dynamics for avatars, which combines detailed real-world measurements, signal analysis, and perceptual experiments to generate improved synthetic eye movement animations.

Publications

Out-of-focus eye tracker configuration Brendan John, Sophie Jörg, Sanjeev Koppal, and Eakta Jain
The Security-Utility Trade-off for Iris Authentication and Eye Animation for Social Virtual Avatars.
IEEE Transactions on Visualization and Computer Graphics (TVCG 2020), 2020, Volume 26, Issue 5, pp. 1880-1890.
Sophie Jörg, Andrew T Duchowski, Krzysztof Krejtz, Anna Niedzielska.
Perceptual Comparison of Procedural and Data-Driven Eye Motion Jitter
ACM Symposium on Applied Perception (SAP), September 2019, Article Nb. 7, pp. 1-5.
Andrew T Duchowski, Sophie Jörg, Jaret Screws, Nina A Gehrer, Michael Schönenberg, Krzysztof Krejtz.
Guiding gaze: expressive models of reading and face scanning
Symposium on Eye Tracking Research & Applications (ETRA), June 2019, Article Nb. 25, pp. 1-9.
Krzysztof Krejtz, Andrew Duchowski, Heng Zhou, Sophie Jörg, Anna Niedzielska.
Perceptual evaluation of synthetic gaze jitter
Computer Animation and Virtual Worlds, 2018 Volumne 29, Issue 6, e1745.
Eyes of highly realistic virtual human Sophie Jörg, Andrew Duchowski, Krzysztof Krejtz, and Anna Niedzielska
Perceptual Adjustment of Eyeball Rotation and Pupil Size Jitter for Virtual Characters.
ACM Transactions on Applied Perception (TAP), October 2018, Volume 15, Issue 4, Article No. 24.
Andrew T Duchowski and Sophie Jörg.
Eye Animation
Handbook of Human Motion, Springer, pp. 147-154, October 2016
Eye Andrew T Duchowski, Sophie Jörg, Tyler N Allen, Ioannis Giannopoulos, Krzysztof Krejtz.
Eye Movement Synthesis
ACM Symposium on Eye Tracking Research & Applications (ETRA), March 2016, pp. 147-154.
Eye Andrew Duchowski, Sophie Jörg, Aubrey Lawson, Takumi Bolte, Lech Swirski, and Krzysztof Krejtz.
Eye Movement Synthesis with 1/f Pink Noise
Proceedings of the 8th ACM SIGGRAPH Conference on Motion in Games 2015 (MIG) November 2015, pp. 47-56.
Andrew T Duchowski and Sophie Jörg.
Modeling physiologically plausible eye rotations
Proceedings of Computer Graphics International, June 2015

Data and Models

Head shot of model Cheryl Screenshot of robot model Chip

We have created the Cheryl Model and the Chip Model as well as recorded the gaze data as part of this project. We used them in the publications in TAP 2018 and at SAP 2019, where you can find a brief description of them.

Cheryl Model
Chip Model (robot)
Gaze Data


Funding and Acknowledgments

This research is supported by: NSF IIS-1423189