We know AI is going to stick around. Whether it’s AI, Machine Learning, Deep Learning or by another name, it all stacks up to the same thing: we’re breaking away from fixed algorithms where one equation ‘does it all’ to a much more nuanced approached with a better result. This is true across all industries. Within the Broadcast industry, one way it can be used is in video and audio compression. Want to make an image smaller? Downsample it with a Convolutional Neural Network and it will look better than Lanczos. No surprise, then, that this is coming in full force to a compression technology near you.
In this talk from Comcast’s Dan Grois, we hear the ongoing work to super-charge the recently released VVC by replacing functional blocks with neural-networks-based technologies. VVC has already achieved 40-50% improvements over HEVC. From the work Dan’s involved with, we hear that more gains are looking promising by using neural networks.
Dan explains that deep neural networks recognise images in layers. The brain does the same thing having one area sensitive to lines and edges, another to objects, another part of the brain to faces etc. A Deep Neural Network works in a similar way.
During the development of VVC, Dan explains, neural network techniques were considered but deemed too memory- or computationally-intensive. Now, 6 years on from the inception of VVC, these techniques are now practical and are likely to result in a VVC version 2 with further compression improvements.
Dan enumerates the tests so far swapping out each of the functional blocks in turn: intra- and inter-frame prediction, up- and down-scaling, in-loop filtering etc. He even shows what it would look like in the encoder. Some blocks show improvements of less than 5%, but added together, there are significant gains to be had and whilst this update to VVC is still in the early stages, it seems clear that it will provide real benefits for those that can implement these improvements which, Dan highlights at the end, are likely to require more memory and computation than the current version VVC. For some, this will be well worth the savings.
In this webinar, visual effects and digital production company Digital Domain will share their experience developing AI-based toolsets for applying deep learning to their content creation pipeline. AI is no longer just a research project but also a valuable technology that can accelerate labor-intensive tasks, giving time and control back to artists.
The webinar starts with a brief overview of deep learning and dive into examples of convolutional neural networks (CNNs), generative adversarial networks (GANS), and autoencoders. These examples will include flavors of neural networks useful for everything from face swapping and image denoising to character locomotion, facial animation, and texture creation.
By attending this webinar, you will:
Get a basic understanding of how deep learning works
Learn about research that can be applied to content creation
See examples of deep learning–based tools that improve artist efficiency
Hear about Digital Domain’s experience developing AI-based toolsets
From AWS re:Invent 2017, Michael Koetter from Turner and Bhavik Vyas from AWS explain that Turner is creating a copy of CNN’s 37-year news video library in AWS to take advantage of the cost and architectural benefits of cloud storage.
This project has unique requirements around retrieval times, and Turner partnered with AWS to drive specific capabilities such as those Amazon Glacier expedited and bulk retrieval options. These cloud-based archives can enable Turner to use other cloud-based value-add services, such as AI/ML/search, and media supply chains efficiently. Turner’s global content exploitation strategies call for extensive versioning of content assets required for distribution to different platforms, products, and regions.
Today, this involves complex workflows to derive multiple downstream versions. Adopting the SMPTE Interoperable Mastering Format (IMF) and cloud-based object storage, Turner will dramatically simplify these workflows by enabling cloud-based automation and elastic scalability. Hear Turner’s strategy, implementation around these media workloads, and lessons learned.
Michael Koetter, SVP, Digital Media Systems, Turner
Bhavik Byas, Global Ecosystem Leader, M&E, AWS
Views and opinions expressed on this website are those of the author(s) and do not necessarily reflect those of SMPTE or SMPTE Members.
This website is presented for informational purposes only. Any reference to specific companies, products or services does not represent promotion, recommendation, or endorsement by SMPTE