Disney has created a cinematic-quality AI tool that automatically makes actors look younger (or older)

Further demonstrating the power of artificial intelligence when it comes to editing images in a photorealistic way, disney researchers have revealed a new aging/de-aging tool that can make an actor look convincingly older or youngerwithout the need for weeks of complex and expensive visual effects work.

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

Visual effects are a powerful filmmaking tool, but there are plenty of reasons to find ways to make them easier to create. of lighten the load on already overworked and underpaid artists, to make the tools accessible to filmmakers not working with huge budgets the size of Hollywood. Of course, even for large studios, there is also a profit motive in being able to automate this kind of work.

That’s why companies like Disney are investing 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 could generate face swap videos with sufficient quality and resolution to be used for professional filmmaking (instead of questionably low-res GIFs shared on the Internet). This year, researchers are demonstrating a new tool that harnesses AI tricks to make actors look older or younger, minus the weeks of work usually required to perfect these types of shots.

Using neural networks and machine learning to age or age a person has been tried before, and while the results were compelling enough when applied to still images, they hadn’t produced photorealistic results. on moving video, with temporal artifacts appearing and disappearing. from frame to frame, and the person’s appearance sometimes becomes unrecognizable as the edited video plays.

To create an anti-aging artificial intelligence tool that was ready for the demands of Hollywood and flexible enough to work on moving images or shots where an actor might not always be looking directly at the camera, Disney researchers, like detailed 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 test subjects, and these results were then used to train a new neural network called FRAN (face re-aging network).

When FRAN receives an input photo, instead of generating an altered photo, it predicts which parts of the face would change with age, such as adding or removing wrinkles, and these results are then overlaid on the face. of origin. visual information channel added. This approach accurately preserves the look and identity of the performer, even when their head moves, when their face looks around, or when the lighting conditions of a shot change over time. It also allows AI-generated changes to be tweaked and tweaked by an artist, which is an important part of VFX work: making the changes blend seamlessly into a shot so that the changes are invisible to a audience.