Ahead of schedule ...

Back in April of 2019, yours truly posted a blurb titled Just a matter of time, describing the very real possibility that digital actors will replace organic ones due to cost savings and ability to seamlessly integrate these entities into videos without having to deal with the agita of inflated egos, bloated salaries and production delays caused by the actor(s) in question because if the video's good, the raison d'ete to deal with said actor A for 20 million becomes questionable at best. Seems Unreal Engine has shot the first salvo in turning this possibility into a viable reality. 

MetaHuman Creator sets a new benchmark for both the believability of digital humans, and also for the ease of creating them. You can directly manipulate facial features, adjust skin complexion, and select from preset body types, hairstyles, clothing, and more. You can even edit your character’s teeth!

Imagine game characters that will blow your players’ minds, digital doubles on the latest virtual production set that will stand up to close-up shots, virtual participants in immersive training scenarios you can’t tell from the real thing: the possibilities for creators are limitless.

Build time

Bringing compelling real-time digital humans to life is incredibly challenging and time-consuming. It can take months of research, costly scanning equipment, and an army of tech artists. What if we could make the process radically simpler, faster, and more scalable—without compromising on quality?

We’re excited to share a sneak peek at MetaHuman Creator, a new tool that will empower anyone to create a bespoke photorealistic digital human, fully rigged and complete with hair and clothing, in a matter of minutes.

Into the rabbit hole ...

Have you ever encountered a lifelike humanoid robot or a realistic computer-generated face that seem a bit off or unsettling, though you can’t quite explain why?

Take for instance AVA, one of the “digital humans” created by New Zealand tech startup Soul Machines as an on-screen avatar for Autodesk. Watching a lifelike digital being such as AVA can be both fascinating and disconcerting. AVA expresses empathy through her demeanor and movements: slightly raised brows, a tilt of the head, a nod.

By meticulously rendering every lash and line in its avatars, Soul Machines aimed to create a digital human that is virtually undistinguishable from a real one. But to many, rather than looking natural, AVA actually looks creepy. There’s something about it being almost human but not quite that can make people uneasy.

Like AVA, many other ultra-realistic avatars, androids, and animated characters appear stuck in a disturbing in-between world: They are so lifelike and yet they are not “right.” This void of strangeness is known as the uncanny valley.

The uncanny valley graph created by Masahiro Mori: As a robot’s human likeness [horizontal axis] increases, our affinity towards the robot [vertical axis] increases too, but only up to a certain point. For some lifelike robots, our response to them plunges, and they appear repulsive or creepy. That’s the uncanny valley.