HomeTechnologyArtificial intelligenceDisney Made an AI Tool That Automatically De-Ages Actors

Disney Made an AI Tool That Automatically De-Ages Actors

Further demonstrating the power of artificial intelligence when it comes to photorealistic editing of footage, researchers at Disney have unveiled a new aging/aging tool that can makes an actor look convincingly older or youngerwithout the need for weeks of complicated and expensive work on visual effects.

When watching a blockbuster like the one from 2018 Ant-Man and the Wasp, most viewers can easily recognize the work of the many visual effects studios contributing to these films, what with their flashy moments where Ant-Man shrinks or grows to gargantuan proportions. But sometimes it’s the more subtle VFX work that’s the hardest to achieve photorealistic results with, like the shots with younger versions of actors Michelle Pfeiffer and Michael Douglas. To get results like those seen in the movie, talented performers must either spend weeks erasing wrinkles and other telltale signs of age from an actor’s face, or replace it entirely with a computer-generated doppelgänger.

Visual effects are a powerful tool in moviemaking, but there are plenty of reasons to find ways to make them easier; from easing the burden of already overworked and underpaid performers, to make the tools accessible to filmmakers who don’t work with huge Hollywood budgets. Of course, even for large studios, there is a profit motive to be able to automate this kind of work as well.

That’s why companies like Disney invest in research to advance the art of visual effects, but in recent years these researchers have also explored how artificial intelligence can simplify VFX work. Two years ago, Disney Research Studios developed AI-powered tools that can generate face swap videos with enough quality and resolution to be used for professional movie shoots (rather than as questionable low-resolution GIFs shared on the web). This year, the researchers are demonstrating a new tool that uses AI tricks to make actors look older or younger, minus the weeks of work usually required to perfect those kinds of shots.

Production ready Facial aging for visual effects

Using neural networks and machine learning to age or age a person has already been attempted, and while the results are convincing enough when applied to still images, they had not yielded photorealistic results on moving video, with temporal artifacts appearing and disappearing from frame to frame, and the person’s appearance occasionally becomes unrecognizable as the modified video plays.

To create an age-changing AI tool that was ready for the demands of Hollywood and flexible enough to work on moving images or shots where an actor isn’t always looking directly at the camera, the Disney researchers, as described in a recently published article, first created a database of thousands of randomly generated synthetic faces. Existing machine learning aging tools were then used to age and age these thousands of non-existent subjects, and those results were then used to train a new neural network called FRAN (face re-aging network).

A step-by-step illustration of how FRAN generates aging/ageing changes that are applied to the original input plane.

When FRAN gets an input headshot, instead of an altered headshot, it predicts which parts of the face would change with age, such as adding or removing wrinkles, and then overlays those results as an extra layer over the original face. channel of added visual information. This approach accurately preserves the artist’s appearance and identity, even when the head moves, when the face looks around, or when the lighting conditions in a shot change over time. It also allows the changes generated by the AI ​​to be modified and tweaked by an artist, which is an important part of VFX work: blending the changes perfectly in a shot so that the changes are invisible to an audience.

Must Read
Madonna Using Rap Music For Clout On TikTok Is Pathetic And Truly Disturbs My Spirit
RELATED ARTICLES

LEAVE A REPLY

Please enter your comment!
Please enter your name here

Most Popular

Recent Comments