September 27-30, 2021
Seattle, Washington, USA + Virtual
View More Details & Registration

The Sched app allows you to build your schedule but is not a substitute for your event registration. You must be registered for Open Source Summit + Embedded Linux Conference + OSPOCon 2021 to participate in the sessions. If you have not registered but would like to join us, please go to the event registration page to purchase a registration.

This schedule is automatically displayed in Pacific Daylight Time (UTC -7). To see the schedule in your preferred timezone, please select from the drop-down menu to the right, above "Filter by Date." The schedule is subject to change.

IMPORTANT NOTE: Timing of sessions and room locations are subject to change.

Back To Schedule
Wednesday, September 29 • 4:55pm - 5:45pm
(Virtual) Embedded Deep Learning Super Resolution on GStreamer using ONNX Inference Runtime - Aaron Boxer & Marcus Edel, Collabora Inc.

Sign up or log in to save this to your schedule, view media, leave feedback and see who's attending!

Feedback form is now closed.
Video streaming has recently experienced tremendous growth, but delivery quality remains critically dependent on network bandwidth. To mitigate bandwidth limitations, most video is compressed, resulting in image artifacts, noise, and blur. One compression method involves transmitting images at lower resolution and then applying up-scaling a.k.a. super-resolution (SR) on the received image to regain initial scale. A new class of techniques known as deep learning super-resolution (DLSR) have recently been developed to dramatically improve SR image quality. Despite their excellent performance, DLSR methods cannot be easily applied to real-world applications due to their heavy computational requirements. In this talk, we present our accurate and lightweight neural network for video super-resolution. We also discuss our implementation of this network on the Khadas VIM3 using ONNX Runtime, a cross-platform inference accelerator, running on GStreamer, everyone's favorite open-source multimedia framework.


Marcus Edel

Machine Learning Engineer, Collabora Ltd.
Marcus Edel is a software engineer in the machine-learning team at Collabora, Inc. where he leads the effort to optimise and apply deep networks for inference, with a focus on embedded devices. Marcus completed his graduate studies in 2020 with a focus on fast algorithms for core... Read More →

Aaron Boxer

Senior Software Engineer, Collabora Inc.
Aaron Boxer is a mathematician and developer, and has been building open-source systems since 2009. He enjoys the simple pleasure of squeezing every last ounce of performance out of both hardware and software. He currently works for Collabora and is based out of Toronto, Canada.

Wednesday September 29, 2021 4:55pm - 5:45pm PDT
MeetingPlay Platform + Virtual Learning Lab
  AI & Data, AI on the Edge