Towards Low-Power and Internet-Scale Mixed Reality
Low power consumption and scalability are the key properties of augmented reality (AR) yet to be realized to attract more users and drive new applications. Towards low-power single-user AR, we develop a novel framework, MARLIN, which only uses a DNN as needed, to detect new objects or recapture objects that significantly change in appearance. When multiple AR users collaborate in a common space, we propose FreeAR that employs collaborative time slicing to distribute compute-heavy AR tasks such as SLAM and DNNs across devices, and leverages P2P communications for message exchanges, to achieve a low energy footprint without edge infrastructure. With cellular infrastructure, AR devices can communicate with cloud servers to offload heavy computations. However, we discover that when multiple users communicate over cellular networks, AR applications experience high latencies. We characterize and understand the root causes of high latencies and perform a first-of-its-kind measurement study. Based on the study, we propose network-aware and network-agnostic AR solutions that help ramp up AR goodput by ~40-70%.
Date and Time
Location
Hosts
Registration
- Date: 09 Mar 2023
- Time: 04:00 PM to 05:00 PM
- All times are (UTC-05:00) Eastern Time (US & Canada)
-
Add Event to Calendar
- New Jersey Institute of Technology
- University Heights
- Newark, New Jersey
- United States 07102
- Building: Electrical and Computer Engineering Center Suite 200
- Room Number: The Lewis P. and Julia Kiernan Conference Room
- Contact Event Host
-
Tao Han, Ph.D.
Associate Professor, NJIT, Tao.Han@njit.edu
- Co-sponsored by New Jersey Institute of Technology
- Starts 21 February 2023 12:30 PM
- Ends 09 March 2023 05:00 PM
- All times are (UTC-05:00) Eastern Time (US & Canada)
- No Admission Charge
Speakers
Dr. Kittipat Apicharttrisorn
Towards Low-Power and Internet-Scale Mixed Reality
Low power consumption and scalability are the key properties of augmented reality (AR) yet to be realized to attract more users and drive new applications. Towards low-power single-user AR, we develop a novel framework, MARLIN, which only uses a DNN as needed, to detect new objects or recapture objects that significantly change in appearance. When multiple AR users collaborate in a common space, we propose FreeAR that employs collaborative time slicing to distribute compute-heavy AR tasks such as SLAM and DNNs across devices, and leverages P2P communications for message exchanges, to achieve a low energy footprint without edge infrastructure. With cellular infrastructure, AR devices can communicate with cloud servers to offload heavy computations. However, we discover that when multiple users communicate over cellular networks, AR applications experience high latencies. We characterize and understand the root causes of high latencies and perform a first-of-its-kind measurement study. Based on the study, we propose network-aware and network-agnostic AR solutions that help ramp up AR goodput by ~40-70%.
Biography:
Dr. Kittipat Apicharttrisorn is a networks researcher at Nokia Bell Labs after finishing his postdoctoral training at Carnegie Mellon University. He received Ph.D. in Computer Science from University of California, Riverside, working on low-power and low-latency mobile augmented reality. He was a recipient of best paper runner-up awards from ACM SenSys in 2019 and IEEE SECON in 2020. His research interests include mixed reality, networked systems, and wireless communications.
Address:United States