“Breaking the Low Sample Rate Equals Low Power Paradigm Using an Event Based Vision Approach for Hand Tracking in AR” by Page, Baesso and Clark – ACM SIGGRAPH HISTORY ARCHIVES

“Breaking the Low Sample Rate Equals Low Power Paradigm Using an Event Based Vision Approach for Hand Tracking in AR” by Page, Baesso and Clark

  • ©

Conference:


Type(s):


Title:


    Breaking the Low Sample Rate Equals Low Power Paradigm Using an Event Based Vision Approach for Hand Tracking in AR

Organizer(s)/Presenter(s):



Description:


    This demo from Ultraleap presents the first hand tracking pipeline using event cameras on an AR headset. Motivated by event cameras’ ability to break the frame imaging paradigm of low power equates to low sample rate moves us closer to low power spatial computing in the glasses form factor.

References:


    [1]
    Leap Motion. 2018. Project North Star. https://blog.leapmotion.com/master-reality-project-northstar/.

    [2]
    Prophesee. 2023. Prophesee GenX320. https://www.prophesee.ai/event-based-sensor-genx320/.

    [3]
    Viktor Rudnev, Vladislav Golyanik, Jiayi Wang, Hans-Peter Seidel, Franziska Mueller, Mohamed Elgharib, and Christian Theobalt. 2021. EventHands: Real-Time Neural 3D Hand Pose Estimation From an Event Stream. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). 12385?12395.

    [4]
    StereoKit. 2023. StereoKit. https://stereokit.net/.


ACM Digital Library Publication:



Overview Page:



Submit a story:

If you would like to submit a story about this experience or presentation, please contact us: historyarchives@siggraph.org