“Beyond foveal rendering: smart eye-tracking enabled networking (SEEN)” by Tollmar, Lungaro, Valero and Mittal
Conference:
Type(s):
Entry Number: 79
Title:
- Beyond foveal rendering: smart eye-tracking enabled networking (SEEN)
Presenter(s)/Author(s):
Abstract:
Smart Eye-tracking Enabled Networking (SEEN) is a novel end-to-end framework using real-time eye-gaze information beyond state-of-the-art solutions. Our approach can effectively combine the computational savings of foveal rendering with the bandwidth savings required to enable future mobile VR content provision.
References:
J. A. Boluda, F. Pardo, T. Kayser, J. J. Perez, and J. Pelechano. 1996. A new foveated space-variant camera for robotic applications. In Proceedings of Third International Conference on Electronics, Circuits, and Systems (1996-10), Vol. 2. 680–683 vol.2. Google ScholarCross Ref
Xavier Corbillon, Alisa Devlic, Gwendal Simon, and Jacob Chakareski. 2016. Viewport-Adaptive Navigable 360-Degree Video Delivery. (2016). arXiv:1609.08042Google Scholar
Tarek El-Ganainy and Mohamed Hefeeda. 2016. Streaming Virtual Reality Content. (2016). arXiv:1612.08350 http://arxiv.org/abs/1612.08350Google Scholar
Brian Guenter, Mark Finch, Steven Drucker, Desney Tan, and John Snyder. 2012. Foveated 3D Graphics. 31, 6 (2012), 164:1–164:10. Google ScholarDigital Library
Evgeny Kuzyakov and David Pio. 2016. Next-generation video encoding techniques for 360 video and VR. (2016). https://code.facebook.com/posts/1126354007399553/next-generation-video-encoding-techniques-for-360-video-and-vr/Google Scholar
Pietro Lungaro and Konrad Tollmar. 2016. Eye-gaze Based Service Provision and QoE Optimization. In PQS 2016 5th ISCA/DEGA Workshop on Perceptual Quality of Systems (2016). 6–10. Google ScholarCross Ref
Simon Parkin. 2016. Nvidia Eye-tracking technology could make virtual reality much clearer. (2016). https://www.technologyreview.com/s/601941/nvidias-eye-tracking-tech-could-revolutionize-virtual-reality/Google Scholar
Keyword(s):
Acknowledgements:
This work is supported by Vinnova 2016-01854 and done by KTH, Tobii Technology and Ericsson Research.
