GTC Shows How to Reinvent Virtual Collaboration and the Video Communication Experience

by Alex Qi

AI has been instrumental in providing exciting features and improving quality and operational efficiency for conferencing, media delivery and content creation partners.

However, building high-quality, real-time, AI-powered effects that can run on local hardware or in the cloud is difficult and developers will benefit from powerful tools that are both scalable and customizable.

NVIDIA Maxine is a real-time AI platform that’s reinventing the virtual collaboration and video communication experience. At GTC, running April 12-16, people new to AI or those looking to improve their broadcast and video conferencing solutions can get up to speed on Maxine’s capabilities and see examples of it at work.

Maxine offers:

  • an end-to-end workflow through pre-trained, state-of-the-art models and sample applications.
  • multiple high-quality, real-time features that are GPU accelerated through an optimized deep learning pipeline.
  • the ability to run everywhere on NVIDIA GPUs: PC, data center and cloud.

Attend the technical talks below during GTC to learn more about the Maxine platform.

How NVIDIA’s Maxine Changed the Way We Communicate

Avaya Spaces built on CPaaS makes capabilities associated with meetings available in contact centers. With AI noise elimination, agents and customers can hear each other in noisy environments. Learn about the art of what’s possible for unique video conferencing experiences by Avaya with NVIDIA AI.

Session time: 11 a.m. PT on Wednesday, April 14. Register here.

Maxine and Headroom Takes the Work out of Meetings with More-Human Video Conferencing

Join Headroom to learn how to apply the latest AI research on real-time streams for a more-human video-conferencing application and explore how to employ generative models for super-resolution, giving order-of-magnitude reduced bandwidth. Headroom will also show how a new solution for saliency segmentation delivers crisp virtual backgrounds.

Session time: 8 a.m. PT on Wednesday, April 14. Register here.

How to Process Live Video Streams on Cloud GPUs Using NVIDIA Maxine SDK

Learn how to use NVIDIA’s Maxine Video Streaming SDK for processing live streaming content in real time. BeLive will cover the basic concepts of the video SDK, how to run the various video effects provided with it, and how to use the numeric results to create visually stunning effects.

Session time: 11 a.m. CET on Tuesday, April 13. Register here.

NVIDIA Maxine: An Accelerated Platform SDK for Developers of Video Conferencing Services

Connect with experts in this session to learn about the latest updates to NVIDIA Maxine, such as how applications based on Maxine can reduce video bandwidth usage down to one-tenth of H.264 using AI video compression. Also see the latest innovations from NVIDIA research, such as face alignment, gaze correction, face re-lighting and real-time translation, in addition to capabilities such as super-resolution, noise removal, closed captioning and virtual assistants.

Session time: 9 a.m. PT on Friday, April 16. Register here.

Advances in NVIDIA Video Technologies: Codecs, AI Compression and Optical Flow Applications

Take a deep technical dive into recent advances in NVIDIA video technologies, specifically related to encoding/decoding (video codecs), upcoming AI-based compression techniques, and the optical flow SDK and its applications.

Session time: 8 a.m. CET on Thursday, April 15. Register here.

And don’t miss GTC’s opening keynote address from NVIDIA CEO Jensen Huang, on April 12 at 8:30 a.m. Pacific time.