Ziva Dynamics has released a beta version of ZRT Face Trainer; a new machine-learning-trained cloud-based facial rigging. In order to showcase its capabilities, Ziva released a GIF that shows the most realistic human expressions you’ve seen in a real-time sequence.
Ziva used Unreal Engine 5 and the following footage was captured in real-time in 4K and with 60fps. Now to be perfectly clear, these facial expressions are not exclusive to Unreal Engine 5. In other words, other developers can implement these facial expressions in their own engines. Ziva simply used Epic’s engine in order to showcase them in real-time.
As Ziva has stated:
“The ZRT Face Trainer is built on a comprehensive library of 4D data and proprietary machine learning algorithms. Within 1 hour, your character mesh is injected with the game industry’s best tech.”
Here are also the key features of ZRT Face Trainer.
- The ZRT Face Trainer is built on a library containing over 15TB of 4D scan data.
- ZRT face puppets can express over 72,000 training shapes, as well as novel face poses.
- ZRT face puppets are only 30MB at runtime and run at real-time frame rates (3ms/frame on a single CPU thread).
It will be interesting to see which games will take advantage of the ZRT Face Trainer in the future. For now, enjoy the following video demonstration!
John is the founder and Editor in Chief at DSOGaming. He is a PC gaming fan and highly supports the modding and indie communities. Before creating DSOGaming, John worked on numerous gaming websites. While he is a die-hard PC gamer, his gaming roots can be found on consoles. John loved – and still does – the 16-bit consoles, and considers SNES to be one of the best consoles. Still, the PC platform won him over consoles. That was mainly due to 3DFX and its iconic dedicated 3D accelerator graphics card, Voodoo 2. John has also written a higher degree thesis on the “The Evolution of PC graphics cards.”
Contact: Email
Angry triggered comments coming : WHY IS SHE A WAMEN WHY IS SHE MANLY REEEEE
JEWS DID THIS REEEEE
yes, why is she ugly? Why is the real model at the beginning prettier? Why they made her uglier? Are they holding back beauty despite they got the technology to do it?
Why is the actress who does Dina in last of us 2 have big tts but they removed them from the game? Why they made Alloy ugly in the game compared to the alpha footage and the concept art and uglier in the sequel?
coz not all people in the world are Victoria Angel models ? I mean look at the mirror you hideous nerd lol
hideous? AHHAHAHAHAH lol, way too assume anyone who isnt you is ugly, this is why they specifically made her uglier to appeal to ugly people like yourself, even though the fact she is the model proves thats not true and pretty people exist.
only militant leftists like you like to look at ugly people in games or movies all the time. this is supposed to be entertainment where you can get away from IRL sh*t and enjoy some time in fantasy land where everyone is smart, funny and gorgeous. even babies are attracted to beautiful people instinctively, science prooved it. Why am I supposed to celebrate mediocrity? Leftism ruined gaming
Cool projection bro. The only people supporting ugly characters are snowflakes who desperately need to feel better about their own shortcomings.
Nothing angry or triggered about complaining that a woman, looks like a man. Especially one which is supposed to be highlighting a product.
I’d go in to the very basics of advertisement and their connection to attractive people, but folks like you don’t care for facts, just your hilariously hypersensitive feelings, and the self conscious misery you induce on yourselves.
Before i even scrolled down to read the comments
the first thing i thought was ,looks like a butch lezzer/Rugby player.
So if i thought that ,it must be true.
Take your pills.
only thing triggering is they got the homeliest girl to do it. why couldn’t they get someone easier to look at?
So the model and all it’s little hairs and details looks good…but the lip movement is STILL off. Like, what’s the problem with this stuff?
I get it’s a totally different way of doing things but even L.A. Noire could sit there and straight record faces 1:1, yet sitting here recording her face 1:1 still leads to this Uncanny Valley lip-syncing that sort of looks right but still totally doesn’t.
sorry kiddo , the fox engine used in mgsv ground zeroes and phantom pain both had better character models as compared to crapcoms engine ,
No doubt its graphically inferior to Capcoms RE engine but here I am talking specifically about character models, I am not a die hard fan of mgs games , I have just played them , even the character models in kojimas death stranding are way better then the ones displayed in RE engine
IT’S MA’AM! Now with more polygons than ever.
lol
this was pretty interesting. and this was done in a matter of hours. without months of extra facial anim tweaking. something that is constantly skimmed in comparison topics. of course if you spend months on tweaking animations and skin shaders they will look better than what can be achieved in some hours.
the main purpose of this workflow pipeline was to demonstrate the tool’s results while spending less time. (roughly 4-5 hrs worth of work) you can always go back and add more “lisps” and “snares” in the lip-syncing. it’s very impressive work none the less.
so glad that this was mentioned, because gamers do tend to compare mo-cap work that took whole developer teams years worth of joint effort to produce. compared to hours of spare time. naturally 3 years worth of attention to detail seeking will be more polished. but that is not the purpose of the tool’s demonstration.
Scary how vicSims can be created for all sorts of scenarios, images of old “scanned” low res photos don’t have to be so sharp for people to believe it was a real person. September Clues has more info on how this is used btw, used in lots of the scripted scenarios of “history” that’s for sure.
They should really consider building a survival horror game around that face. I was scared the moment I saw it. Jesus….
Great quality animations, a step forward.
…and you will never see something like this in a videogame, but probably a movie.
yes we will. go watch Left of Us Part 2. the game is wack but the facial animations are amazing. this isn’t like leaps and bounds ahead of that.