The greenscreen is a staple of visual effects — and it may stick around even in the age of AI “magic.” The video above explains why.
It turns out that greenscreens, while imperfect, provide certain background separation benefits that are tough for AI to replicate due to the way it’s been trained and the limitations of available data. Preparation can help improve results, but, ultimately, AI tools will remain one in a suite of options rather than a greenscreen killer.
- Read Soumyadip (Roni) Sengupta’s papers, including links to his greenscreen work.
- If you want to try the latest breakthrough in image segmentation, Meta’s demo lets you upload your own images.
- Runway ML has a variety of tools that sit on top of AI infrastructure, allowing you to play with all sorts of applications. Take a look at their documented process.
- If you want to learn more, you can read about image matting on an important dataset.
You can find this video and the entire library of Vox’s videos on YouTube.
We're here to shed some clarity
One of our core beliefs here at Vox is that everyone needs and deserves access to the information that helps them understand the world, regardless of whether they can pay for a subscription. With the 2024 election on the horizon, more people are turning to us for clear and balanced explanations of the issues and policies at stake. We’re so grateful that we’re on track to hit 85,000 contributions to the Vox Contributions program before the end of the year, which in turn helps us keep this work free. We need to add 2,500 contributions this month to hit that goal. Will you make a contribution today to help us hit this goal and support our policy coverage? Any amount helps.
- How does AI actually work? 4
How is AI changing society?
- What the stories we tell about robots tell us about ourselves
- Silicon Valley’s vision for AI? It’s religion, repackaged.
- What will love and death mean in the age of machine intelligence?
- What if AI treats humans the way we treat animals?
- Can AI learn to love — and can we learn to love it?
- Black Mirror’s big AI episode has the wrong villain
- The ad industry is going all-in on AI
- The looming threat of AI to Hollywood, and why it should matter to you
- What gets lost in the AI debate: It can be really fun
- How unbelievably realistic fake images could take over the internet
- Robot priests can bless you, advise you, and even perform your funeral
- AI art freaks me out. So I tried to make some.
- How fake AI images can expand your mind
- AI art looks way too European
- An AI artist explains his workflow
- What will stop AI from flooding the internet with fake images?
- You’re going to see more AI-written articles whether you like it or not
- How “windfall profits” from AI companies could fund a universal basic income
Is AI coming for your job?
- AI is flooding the workplace, and workers love it
- If you’re not using ChatGPT for your writing, you’re probably making a mistake
- Maybe AI can finally kill the cover letter
- Americans think AI is someone else’s problem
- Mark Zuckerberg’s not-so-secret plan to join the AI race
- The hottest new job is “head of AI” and nobody knows what they do
- Why Meta is giving away its extremely powerful AI model
Should we be worried about AI?
- Four different ways of understanding AI — and its risks
- AI experts are increasingly afraid of what they’re creating
- AI leaders (and Elon Musk) urge all labs to press pause on powerful AI
- The case for slowing down AI
- Are we racing toward AI catastrophe?
- The promise and peril of AI, according to 5 experts
- An unusual way to figure out if humanity is toast
- How AI could spark the next pandemic
- AI is supposedly the new nuclear weapons — but how similar are they, really?
- Don’t let AI fears of the future overshadow present-day causes
Who will regulate AI?
- The $1 billion gamble to ensure AI doesn’t destroy humanity
- Finally, a realistic roadmap for getting AI companies in check
- Biden sure seems serious about not letting AI get out of control
- Can you safely build something that may kill you?
- Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI
- Scared tech workers are scrambling to reinvent themselves as AI experts
- Panic about overhyped AI risk could lead to the wrong kind of regulation
- AI is a “tragedy of the commons.” We’ve got solutions for that.
- The AI rules that US policymakers are considering, explained
Sign up for the newsletter Future Perfect
Each week, we explore unique solutions to some of the world's biggest problems.