How AI makes Disney magic happen
Erika Varis Doggett, research scientist at the Walt Disney Studios StudioLAB, has a pretty awesome job: In collaboration with partners such as Hewlett Packard Enterprise, as well as studio creatives, technologists, and business executives, Doggett and her team of engineers work on the cutting edge of filmmaking, exploring ways to apply artificial intelligence, machine learning, and other technologies at every stage of the process.
Or, in her words, "We get to build really cool stuff together, all in the name of really seeing what we can do with innovative storytelling today."
That means keeping an eye on AI and other technologies emerging from both startup and established tech companies, and experimenting with how they can be used to enhance everything from animation techniques to video production, with the overall goal of making "the lives and jobs of our studio stakeholders much, much easier," Doggett says.
In this episode of Tech Talk, host Robert Christiansen, vice president of strategy in HPE's Office of the CTO, sits down with Doggett for a behind-the-scenes look at "the latest and greatest" in moviemaking technology at Disney studios.
AI gives QC experts 'superpowers'
An area ripe for AI-driven improvements is video quality control, Doggett says, noting the high bar both Disney and its fans set means every pixel counts.
To meet those standards, highly skilled studio QC experts "watch every version of every film before it goes out for distribution to make sure that there aren't any errors in the image," Doggett explains. "As you can imagine, there's a lot of different pixels on an image, particularly when you're talking just a standard HD resolution, which is about 2K, but then expanding up into some of the latest 4K formats. There's a lot of spots that could potentially be wrong."
That's where AI and automated tools come in, helping Disney QC experts find errors more quickly so they can focus on 'the next stage of decision-making,' " Doggett says. "We want to enable our QC experts to be able to do more with less time."
"We want to enable our QC experts to be able to do more with less time," she says. "By providing automated tools to do parts of that QC workflow, we get to give them superpowers."
Please read: AI by the numbers
Another AI application to emerge from StudioLAB is a machine learning model trained on clean images that don't have anomalies in them. "It's trained to say, 'OK, given the surrounding pixels, can I generate what is supposed to be on the inside section?'" Doggett explains. "What we're doing is we're actually having it go across the entire image so that it can inpaint every single pixel."
More storytelling, fewer tedious tasks
With AI now performing such complex tasks across the filmmaking process, does that mean it will eventually take over every facet of filmmaking? "No, no," Doggett says.
"We want to let our people do the things that they are so good at because the creative storytellers that we have at the Walt Disney Company are incredible," she says. "What we want to do is instead give them new tools to explore and see what is possible. Can we do different kinds of stories with technology? Are there different mediums in which we can tell stories, or are there ways that I can do this other tedious part of the filmmaking process faster?"
In the end, she says, "I want to come back to that notion of, we want to give our humans superpowers."
We want to let our people do the things that they are so good at because the creative storytellers that we have at the Walt Disney Company are incredible.
This article/content was written by the individual writer identified and does not necessarily reflect the view of Hewlett Packard Enterprise Company.