And it's a pretty weak showing. The stiff animation and bad lip sync immediately gives it away to me. And the fact that the CGI Huang is shown ~15 times smaller than the real one is very damning.
> It's not clear exactly which part of the keynote speech features CGI Huang (which is what makes the replica so impressive), but if you jump to this part of the presentation you can see Huang magically disappear and his kitchen explode into multiple different 3D models.
I was going to comment something like "yeah, yeah, everyone's an expert, it's easy to say you can spot the CGI once you've been told it's there", but then I looked at the video and... wow, that really is a pretty weak showing!
If you follow the 'VFX artists react' series on YouTube you learn what give CGI humans away pretty easily. Getting CGI humans right is very difficult and few VFX houses, with decades of experience, get it right even with post processing, let alone doing it in real time.
CGI Jensen looks like he came out of a 2009 videogame. Nvidia may have the tech but you can tell it lacks the artistic supervision of a proper VFX house so the end result looks like something their engineers put together in a last minute crunch (which is probably what happened).
I can't think of a time when I've been fooled by CGI (though, of course, I wouldn't be aware of being fooled if I was, so it's a catch-22).
I really hate when movies throw in a CGI character expecting it to come off as real. It pulls you out of the movie in a way that normal over-the-top action CGI doesn't. I remember watching the recent Star Wars movies and being jerked out of the flow by CGI Princess Leah and some other characters (whoever the villainous old man was in that movie).
I'd be interested to see any videos of CGI faces that can fool experts.
Slightly off-topic, but still anecdotal how far CGI has come, I recently showed my dad who hasn't played any video games for at least 20 years this [0] video of the current MS Flight Simulator. It is produced in a documentary style, so there are no real cues to it being a game. After watching it together, my dad said: "Yeah that's a nice documentary about this difficult airport, but I thought you wanted to show me that new game?".
You can imagine his face when I told him that we've in fact watched just that.
With respect to your dad, how did he explain the shots outside of the airplane? Did he interpret that as a helicopter flying around the airplanes with a video camera?
Also, I'd like to point out that Microsoft has skillfully choosen scenes that are "easy" to create: airplanes with smooth shapes, buildings from long distances and low detail, landscapes that don't include movement (no grass moving in the wind or waves lapping on the shore). MS set them selves up for success here.
I get your point, but "I can't think of a time when I've been fooled by CGI" is a tautology: you remember = you weren't fooled. If you had been fooled, chances are you wouldn't remember.
There are videos from CGI artists, e.g. Corridor Crew, that break down really good CGI, which is almost entirely invisible to the non-expert eye. That is in fact the best kind of CGI: the one that enhances reality so seamlessly that it's almost impossible to pick apart. Quite entertaining and informative videos.
Although if you're fooled, and find out later, I think there's a strong human tendency to re-write the internal narrative.... "Really, I could kind of tell all along." In which case it's not so clear how you'd "remember" things later.
You laid out how: if you don't re-write your internal narrative
You're right that theres a possibility that someone is fooled and never finds out, and another possibility that someone is fooled, finds out later, and claims they never thought it was real. However, it is very clear that it's possible to be fooled and find out later.
I have one: Ping Pong, the Japanese film from 2002. After watching the bonus features about how they developed the actors' individual playing styles, they revealed that the balls were entirely CGI animated. That let the actors focus on the precision of their movements, without worrying about actually volleying!
The balls looked a bit odd in the film, but I figured it was simply an artifact of 23fps film capturing a small plastic ball moving at high speed. I never would have guessed it was all CGI. I think I'd seen the movie three times before buying the DVD and watching the special features, years later. So I was fooled in the mid-00s and again in the late 10s.
I'm not so sure that it's easy to tell the difference between CGI and reality. Sometimes scenes in movies look really fake, but aren't actually CGI. The way scenes are lit and the heavy makeup actors end up wearing can make it seem like a real scene looks fake.
Objects mostly just sit there, or move in more predictable ways. But when it comes to faces and bodies, we're super-tuned to facial detail, and are heavily primed to read emotions and context from facial details and from posture.
So if any part of that falls into uncanny valley, the whole experience looks wrong.
Back when animations were done by hand, Disney's animators handled this by rotoscoping (drawing over...) live action, which created very convincing results even when the movements were exaggerated for effect.
Doing the same with CGI without a template is an unbelievably difficult challenge. It's much easier to create cartoonish exaggerations than to get spot-on perfect realism.
The best results I've seen are analogous to a modern version of rotoscoping. It involves creating a fully animated 3d model of a person and then using a well trained deep fake of the actor's face in combination.
It would be interesting if costume people could figure out how to give the reverse effect, where they dress someone up like they are a bad CGI. That would be pretty funny! (also it would make a great Halloween costume)
> [Max Headroom] was called "the first computer-generated TV personality", although the computer-generated appearance was achieved with an actor in prosthetic make-up and harsh lighting, in front of a blue screen
In the case of the nVidia presentation, it's quite obvious from the video where it's CGI Ceo: Awkward standing position, stiff arms and fairly inarticulate fingers. He looks fairly suspended, as if there's nothing to convey weight/physics in his movements... however brief.
> CGI Jensen looks like he came out of a 2009 videogame. Nvidia may have the tech but you can tell it lacks the artistic supervision of a proper VFX hous
That's part of the point. If computer software alone can replicate state of the art human effort from 12 years ago, that's what they're showing off. It's not "look how great this rendering is", it's "look how good the AI that made this is".
I don't think you have to watch anything to learn what gives CGI humans away. I don't think anyone has actually managed a truly convincing one yet. This is the closest I've seen:
Rachel's appearance in Blade Runner 2049 was shockingly good to me. (https://www.youtube.com/watch?v=rDx3WwWR6y4) On the other hand, I though Tarkin looked pretty good in Rogue One, and for some people he's a corpse. I don't think the uncanny valley is as consistent among people as folks here are suggesting.
Yeah I thought Tarkin was not convincing (though still really impressive, especially for the time). I totally forgot about Blade Runner - I agree that was really good - better than Star Wars.
The coolest thing about that video is how good it is, but the second coolest thing about that video is the fact that Lucasfilm recently decided to hire the guy that made it.
I'm pretty sure that's SOP for Nvidia conference demos.
Was in a breakout after the main Jensen presentation and the engineer was talking about how they were fiddling with K8s to get the demo to work right, the night before. And this was the money demo in the middle of the presentation.
On the other hand... I actually kind of like a company that half-asses demos. It suggests they're spending their time on more important things.
I jumped around a bit, and I'd say the video looks like a zoom call with poor internet. The portion that was "cg" wasn't too different that conference calls I've been on where the signal is messed up.
That looks like when a typical tv show does a "video game" episode and one of the regular cast members gets a character meant to look like them, but in video game form. It does not look like it was meant to seem human.
After watching the whole making of I also was pretty disappointed of the final result. Each individual part in the making of was pretty solid so I had high expectations.
I guess it was the tight deadline (only a few weeks I think?) that didn't leave them any time to polish the final result.
>> It's not clear exactly which part of the keynote speech features CGI Huang (which is what makes the replica so impressive),
I think what Vice ment to say was "this video was SO boring, we were multitasting on our phone and didn't see anything out the ordinary from the corner of our eyes."
Thanks for the direct link; I thought it was pretty horrible. At this level, if you're going to take the time to show how awesome your stuff is, maybe partner with a talented team to do it on the level of Disney/Pixar.
For journalists, something like that is quite an accusation, and it really doesn’t help anyone to thoughtlessly make it.
Maybe they are stupid, or just have different ideas of what’s newsworthy, or it was a slow news day…whatever. But all of those come down to a difference of opinion, not a statement of fact made without evidence.
“Assume good faith” is in the guidelines here. And while it isn’t explicitly extended to the articles themselves, the reason for including it do extend to other interactions. Mindless cynicism leads to the sort of corrosive distrust that’s eating away at civil societies everywhere.
> Mindless cynicism leads to the sort of corrosive distrust that’s eating away at civil societies everywhere.
...repeated breaking of trust by institutions has earned that. It is unfortunate and it does eat away at our civil society. The solution is to fix the broken institutions and re-gain trust, not to blindly follow them like livestock!
I was judging the couple of seconds before the transition, and thought it wasn't that bad.
Then I focused on the transition, and the jacket lost all the texture. Later I let the transition play through, and saw that lonely character standing there, zoomed away, awkward hand and arm movement, and I cringed.
Why put any amount of effort into it if this is the result? Almost pathetic.
Thanks! I did not immediately realize this since I just jumped to the video. Given the state of the art in various subfields in CGI it would have made it moderately plausible the live CEO would have been rendered as well (in which case it would have been mindbogglingly good).
Given how Nvidia has been with their presentations the last few years, I was entirely expecting Jensen to 100% CGI based on the title. They have a flair for flexing their technology so it would have been entirely on brand for them to do it and then only tell us a year later.
It's quite surprising to me that they actually published the press release. With this quality, it would've probably been better to say nothing and let this one slip quietly.
On the other hand, there's no such thing as bad publicity, I guess ...
> On the other hand, there's no such thing as bad publicity, I guess ...
My pet conspiracy theory is that that old cliché is promoted by publicity companies as false advertising aimed at their own customers, the businesses who buy their ad campaigns, to cover their asses regardless of the end result.
The reason he ended up looking like shit is because it was a combination of dog-fooding their own software (admirable) as well as rushing the production on a tight deadline.
Imagine crunching long hours to make a digital replica of your boss for the hell of it. They even scanned his leather jacket, which is admittedly worthy of a chuckle considering the thing's taken on a life of its own. In the distant future, I imagine the jacket will be embodied with AI and entrusted with carrying the company forward in Jensen's image.
Silicon Valley may have ended years ago, but stuff like this writes itself.
They focus on the wrong thing, in my opinion. What I took away from NVIDIA's announcement was:
NVIDIA is dog-fooding their Metaverse renderer and all the CGI sequences in the keynote were created using it. As someone considering to build a plugin for it, that's great news. If they use it themselves, you can be reasonably optimistic that it won't have any horrible usability bugs. Plus it now integrates with Blender.
So if I had to come up with a headline, it'd be:
"NVIDIA's Photorealistic Keynote Rendering Software now available for Free to Blender Users"
Even the tiny computer-generated keynote part points to something that can nudge humanity forward.
Namely, the possibility of automating bullshit. Endless mission statements, employee narrated stories, and hand gesturing is very valuable. I would pay $10,000 out of my pocket for the opportunity to never do those product hype videos again.
> you can be reasonably optimistic that it won't have any horrible usability bugs
Or alternatively, since they are the ones also building it, they intimately know it's (undocumented) pitfalls and how to work around them and/or they plow through bad DX with a horde of engineers that only a big corporation like them can afford. Dog-fooding doesn't automatically improve a product.
Agreed. I was watching the real Jensen thinking, hmmm seems a bit plastic and lifeless, but the rendering looks very realistic. Turns out that's just Jensen.
They apparently created all slides of the keynote with omniverse in a couple of weeks, and used a lot of technologies for no other reason than just to try them out.
actually that timestamp is deceptive since the frame it opens at is the real jensen. this timestamp shows the cgi jensen and its very obvious due to the distance and animation that it is indeed cgi.
https://youtu.be/eAn_oiZwUXA?t=3761
I simply do not understand why they are pouring so many resources at Omniverse. They’re reinventing the wheels quite a bit. Leads me to believe this is Jensen’s pet project that no one within the company will go against.
From the Vice article: "After this article was published, Nvidia updated its blog post, clarifying that “only 14 seconds of the hour and 48 minute presentation” were animated."
Even Gemini Man was not very convincing with all the money and the time and effort they could spend. I don’t believe any other attempt could produce a better result any time soon.
In Strugatski brothers novel "Monday Begins on Saturday" (first published in 1964) employees substituted their dumb clones for themselves to perform various mind numbing low-intelligence work related activities which their employment at a typical research institution of USSR was full of. And the large West corporations do have a lot of that old socialism feel to them :)
And it's a pretty weak showing. The stiff animation and bad lip sync immediately gives it away to me. And the fact that the CGI Huang is shown ~15 times smaller than the real one is very damning.
> It's not clear exactly which part of the keynote speech features CGI Huang (which is what makes the replica so impressive), but if you jump to this part of the presentation you can see Huang magically disappear and his kitchen explode into multiple different 3D models.
So how much was Vice paid for this article?