Computational Filmmaking

Creative Next: AI Automation at Work - A podcast by Creative Next

How are computational tools changing filmmaking, and how will it change the video content of the future? To explore these topics we welcome Genevieve Patterson, Chief Scientist and Co-Founder of TRASH, to the show. Tools like those offered by TRASH, Genevieve Patterson’s software that uses AI to make and share video, are beginning to edit video automagically for people. While these are currently limited to short, simple, social media-style videos the underlying machine learning technologies are building toward something far more.   Memorable Quotes “The big goal of our app is both to make it so that users can have an Instagram or Photoshop type feeling about  creating beautiful videos, but not having to really understand how editing works.” “My big issue with lots of public use of artificial intelligence, especially in  life threatening situations, in extreme situations that affect people's lives, is that there's no regulatory agency to check whether or not they're working, or achieving the objectives of the law enforcement body or of the citizens.” “I think that TRASH, and other complementary apps, that we're going to make it easier for those people to do their jobs. And because it's easier for them to do their jobs, I think they're going to do more work, and I think that it'll add a lot to creators, creative professionals. think that creative professionals will become even more professional in a sense, because they'll have this new media that they can participate in and create in and advertise in.” “Machine learning systems, the way they're set up, they'll just give you the wrong answer. And you don't know that it's the wrong answer because it's not telling you.” “When you create machine learning systems, those systems can only possibly understand or know the data that is fed to them at the beginning. And it is very easy to feed them the wrong data, to feed them images that don't apply to the context in which the system will be used.” “Google trained a huge deep network, and the thing that deep network was the best at was identifying cat faces. And that's because the cat faces have such a rigid shape. The nose is always shaped in the same way, the eyes are always shaped in the same way, the ears are in the same location. And so finding  out what that pattern was and then being able to match that pattern worked very successfully.” “How do you use image filtering,  signal processing, machine learning, deep learning techniques to change  more than just like the color, although that's often an important thing, but more to change superficial characteristics that apply to an entire frame. How do we change  the behavior of the objects in the film? How do we re-time the film? How do we make people's motions line up with music? How do we completely alter the backgrounds and make it still look photorealistic? That's the ultimate goal of computational filmmaking. “I'm also interested in how  the perspective of  creators who don't have a bias about how films should be made or stories should be presented will give us a whole new look at non-narrative filmmaking, from a maybe even like a different cultural perspective, or not a particularly  human biased perspective. We could get films that are just radically different from films of the last 100 years. And that they'll look really good because we will automate all of the things that are really labor intensive and take a lot of education.” “I'm excited about trying to figure out how to automate that super laborious, manual technique.” “I think that computational filmmaking is going to make it so that more people are making, what we would currently perceive as professional quality film.”   Who You'll Hear Dirk Knemeyer, Social Futurist and Producer of Creative Next (@dknemeyer) Jonathan Follett, Writer, Electronic Musician, Emerging Tech Researcher and Producer of Creative Next (@jonfollett) Genevieve Patterson, Chief Scientist and Co-Founder, TRASH (@GenevieveMP)   Join The Conversation Website & Newsletter: www.creativenext.org Twitter: @GoCreativeNext Facebook: /GoCreativeNext Instagram: @GoCreativeNext   Sponsors GoInvo, A design practice dedicated to innovation in healthcare whose clients are as varied as AstraZeneca, 3M Health Information Services, and the U.S. Department of Health and Human Services. www.goinvo.com  Design Museum Foundation, A new kind of museum, they believe design can change the world. They’re online, nomadic, and focused on making design accessible to everyone. Their mission: bring the transformative power of design everywhere. You can learn about their exhibitions, events, magazine, and more. www.designmuseumfoundation.org BIF, As a purpose-driven firm, BIF is committed to bringing design strategy where it is needed most - health care, education, and public service to create value for our most vulnerable populations. www.bif.is